[ { "full_name": "google-research/google-research", "slug": "google-research-google-research", "url": "https://github.com/google-research/google-research", "owner": "google-research", "name": "google-research", "description": "Google Research", "readme": "Because the repo is large, we recommend you download only the subdirectory of interest:", "stars": 38627, "stars_scraped": 38600, "forks": 8500, "watchers": 782, "language": null, "license": null, "gh_topics": [ "ai", "machine-learning", "research" ], "pushed_at": "2026-08-26", "created_at": "", "archived": false, "paper_ids": [ "2309.15505" ], "owner_type": "Organization", "owner_display": "Google Research", "owner_company": "", "owner_location": "Earth", "owner_url": "https://github.com/google-research", "owner_repos": 359, "owner_followers": 17076, "owner_bio": "", "affiliated_org": "Google DeepMind", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2309.15505", "slug": "finite-scalar-quantization-vq-vae-made-simple", "title": "Finite Scalar Quantization: VQ-VAE Made Simple", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "bulletphysics/bullet3", "slug": "bulletphysics-bullet3", "url": "https://github.com/bulletphysics/bullet3", "owner": "bulletphysics", "name": "bullet3", "description": "Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.", "readme": "", "stars": 14700, "stars_scraped": 14700, "forks": 3091, "watchers": 403, "language": "C++", "license": "NOASSERTION", "gh_topics": [ "computer-animation", "game-development", "kinematics", "pybullet", "reinforcement-learning", "robotics", "simulation", "simulator", "virtual-reality" ], "pushed_at": "2025-10-22", "created_at": "2011-04-12", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Bullet Physics SDK", "owner_company": "", "owner_location": "United States", "owner_url": "https://github.com/bulletphysics", "owner_repos": 2, "owner_followers": 355, "owner_bio": "Bullet Physics development team", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "carla-simulator/carla", "slug": "carla-simulator-carla", "url": "https://github.com/carla-simulator/carla", "owner": "carla-simulator", "name": "carla", "description": "Open-source simulator for autonomous driving research.", "readme": "CARLA is an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform support", "stars": 14328, "stars_scraped": 14300, "forks": 4670, "watchers": 263, "language": "C++", "license": "MIT", "gh_topics": [ "ai", "artificial-intelligence", "autonomous-driving", "autonomous-vehicles", "carla", "carla-simulator", "computer-vision", "cross-platform", "deep-learning", "deep-reinforcement-learning", "imitation-learning", "research", "ros", "self-driving-car", "simulator", "ue4", "unreal-engine-4" ], "pushed_at": "2026-08-26", "created_at": "2017-10-24", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "CARLA", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/carla-simulator", "owner_repos": 37, "owner_followers": 1000, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real", "navigation" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "google-research/vision_transformer", "slug": "google-research-vision-transformer", "url": "https://github.com/google-research/vision_transformer", "owner": "google-research", "name": "vision_transformer", "description": "", "readme": "The models from this codebase were originally trained in https://github.com/google-research/big_vision/ where you can find more advanced code (e.g. multi-host training), as well as some of the original training scripts (e.g. configs/vit_i21k.py for pre-training a ViT, or configs/transfer.py for transfering a model).", "stars": 12683, "stars_scraped": 12700, "forks": 1500, "watchers": 110, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-01", "created_at": "", "archived": false, "paper_ids": [ "2010.11929" ], "owner_type": "Organization", "owner_display": "Google Research", "owner_company": "", "owner_location": "Earth", "owner_url": "https://github.com/google-research", "owner_repos": 359, "owner_followers": 17076, "owner_bio": "", "affiliated_org": "Google DeepMind", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2010.11929", "slug": "an-image-is-worth-16x16-words-transformers-for-image-recognition-at-sc", "title": "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale", "featured": false } ], "topics": [ "foundation-pretraining" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "IDEA-Research/GroundingDINO", "slug": "idea-research-groundingdino", "url": "https://github.com/IDEA-Research/GroundingDINO", "owner": "IDEA-Research", "name": "GroundingDINO", "description": "[ECCV 2024] Official implementation of the paper \"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection\"", "readme": "Shilong Liu , Zhaoyang Zeng , Tianhe Ren , Feng Li , Hao Zhang , Jie Yang , Chunyuan Li , Jianwei Yang , Hang Su , Jun Zhu , Lei Zhang \ud83d\udce7 .", "stars": 10517, "stars_scraped": 10500, "forks": 1100, "watchers": 48, "language": null, "license": null, "gh_topics": [ "object-detection", "open-world", "open-world-detection", "vision-language", "vision-language-transformer" ], "pushed_at": "2024-08-12", "created_at": "", "archived": false, "paper_ids": [ "2303.05499" ], "owner_type": "Organization", "owner_display": "IDEA-Research", "owner_company": "", "owner_location": "China", "owner_url": "https://github.com/IDEA-Research", "owner_repos": 49, "owner_followers": 2941, "owner_bio": "The International Digital Economy Academy (\u201cIDEA\u201d). ", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2303.05499", "slug": "grounding-dino-marrying-dino-with-grounded-pre-training-for-open-set-o", "title": "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection", "featured": false } ], "topics": [ "foundation-pretraining" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "isaac-sim/IsaacLab", "slug": "isaac-sim-isaaclab", "url": "https://github.com/isaac-sim/IsaacLab", "owner": "isaac-sim", "name": "IsaacLab", "description": "Unified framework for robot learning built on NVIDIA Isaac Sim", "readme": "This is the stable release branch for Isaac Lab 3.0.0 Beta 2 and supports Isaac Sim 6.0.0 and 6.0.1. Use the v3.0.0-beta2.patch1 tag for a reproducible release checkout. Active feature development continues on the develop branch.", "stars": 7966, "stars_scraped": 7900, "forks": 3850, "watchers": 63, "language": "Python", "license": "BSD-3-Clause", "gh_topics": [ "isaac-sim", "omniverse-kit-extension", "robot-learning", "robotics" ], "pushed_at": "2026-08-26", "created_at": "2022-11-16", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "NVIDIA Isaac Sim", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/isaac-sim", "owner_repos": 21, "owner_followers": 1720, "owner_bio": "", "affiliated_org": "NVIDIA", "link_sources": [], "papers": [], "topics": [], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "sczhou/ProPainter", "slug": "sczhou-propainter", "url": "https://github.com/sczhou/ProPainter", "owner": "sczhou", "name": "ProPainter", "description": "[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting", "readme": "", "stars": 6916, "stars_scraped": 6900, "forks": 818, "watchers": 66, "language": null, "license": null, "gh_topics": [ "object-removal", "video-completion", "video-inpainting", "video-outpainting", "watermark-removal" ], "pushed_at": "2025-02-19", "created_at": "", "archived": false, "paper_ids": [ "2309.03897" ], "owner_type": "User", "owner_display": "Shangchen Zhou", "owner_company": "Nanyang Technological University", "owner_location": "Singapore", "owner_url": "https://github.com/sczhou", "owner_repos": 13, "owner_followers": 1494, "owner_bio": "Research Assistant Professor at MMLab@NTU. ", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2309.03897", "slug": "propainter-improving-propagation-and-transformer-for-video-inpainting", "title": "ProPainter: Improving Propagation and Transformer for Video Inpainting", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "apple/ml-depth-pro", "slug": "apple-ml-depth-pro", "url": "https://github.com/apple/ml-depth-pro", "owner": "apple", "name": "ml-depth-pro", "description": "Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.", "readme": "We present a foundation model for zero-shot metric monocular depth estimation. Our model, Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high-frequency details. The predictions are metric, with absolute scale, without relying on the availability of metadata such as camera intrinsics. And the model is fast, producing a 2.25-megapixel depth map in 0.3 seconds on a ", "stars": 5683, "stars_scraped": 5700, "forks": 429, "watchers": 56, "language": null, "license": null, "gh_topics": [], "pushed_at": "2025-04-21", "created_at": "", "archived": false, "paper_ids": [ "2410.02073" ], "owner_type": "Organization", "owner_display": "Apple", "owner_company": "", "owner_location": "Cupertino, CA", "owner_url": "https://github.com/apple", "owner_repos": 441, "owner_followers": 39692, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2410.02073", "slug": "depth-pro-sharp-monocular-metric-depth-in-less-than-a-second", "title": "Depth Pro: Sharp Monocular Metric Depth in Less Than a Second", "featured": false } ], "topics": [ "spatial-3d", "foundation-pretraining" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "facebookresearch/moco", "slug": "facebookresearch-moco", "url": "https://github.com/facebookresearch/moco", "owner": "facebookresearch", "name": "moco", "description": "PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722", "readme": "Examples of unacceptable behavior by participants include:", "stars": 5136, "stars_scraped": 5100, "forks": 802, "watchers": 47, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-02-03", "created_at": "", "archived": false, "paper_ids": [ "1911.05722" ], "owner_type": "Organization", "owner_display": "Meta Research", "owner_company": "", "owner_location": "Menlo Park, California", "owner_url": "https://github.com/facebookresearch", "owner_repos": 1436, "owner_followers": 37143, "owner_bio": "", "affiliated_org": "Meta FAIR", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "1911.05722", "slug": "momentum-contrast-for-unsupervised-visual-representation-learning", "title": "Momentum Contrast for Unsupervised Visual Representation Learning", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "google-research/simclr", "slug": "google-research-simclr", "url": "https://github.com/google-research/simclr", "owner": "google-research", "name": "simclr", "description": "SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners", "readme": "", "stars": 4502, "stars_scraped": 4500, "forks": 665, "watchers": 0, "language": null, "license": null, "gh_topics": [ "computer-vision", "contrastive-learning", "representation-learning", "self-supervised-learning", "simclr", "simclrv2", "unsupervised-learning" ], "pushed_at": "2023-05-22", "created_at": "", "archived": true, "paper_ids": [ "2002.05709" ], "owner_type": "Organization", "owner_display": "Google Research", "owner_company": "", "owner_location": "Earth", "owner_url": "https://github.com/google-research", "owner_repos": 359, "owner_followers": 17076, "owner_bio": "", "affiliated_org": "Google DeepMind", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2002.05709", "slug": "a-simple-framework-for-contrastive-learning-of-visual-representations", "title": "A Simple Framework for Contrastive Learning of Visual Representations", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "Robbyant/lingbot-world", "slug": "robbyant-lingbot-world", "url": "https://github.com/Robbyant/lingbot-world", "owner": "Robbyant", "name": "lingbot-world", "description": "Advancing Open-source World Models", "readme": "This repository is no longer actively maintained .", "stars": 4393, "stars_scraped": 4400, "forks": 399, "watchers": 45, "language": null, "license": null, "gh_topics": [ "aigc", "image-to-video", "lingbot-world", "video-generation", "world-models" ], "pushed_at": "2026-07-09", "created_at": "", "archived": false, "paper_ids": [ "2601.20540" ], "owner_type": "Organization", "owner_display": "Robbyant", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Robbyant", "owner_repos": 10, "owner_followers": 1495, "owner_bio": "Intelligence in Action, Benefits for Everyone", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2601.20540", "slug": "advancing-open-source-world-models", "title": "Advancing Open-source World Models", "featured": false } ], "topics": [ "world-models" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "google-research/scenic", "slug": "google-research-scenic", "url": "https://github.com/google-research/scenic", "owner": "google-research", "name": "scenic", "description": "Scenic: A Jax Library for Computer Vision Research and Beyond", "readme": "Scenic is developed in JAX and uses Flax .", "stars": 3821, "stars_scraped": 3800, "forks": 480, "watchers": 35, "language": null, "license": null, "gh_topics": [ "attention", "computer-vision", "deep-learning", "jax", "research", "transformers", "vision-transformer" ], "pushed_at": "2026-08-10", "created_at": "", "archived": false, "paper_ids": [ "2103.15691" ], "owner_type": "Organization", "owner_display": "Google Research", "owner_company": "", "owner_location": "Earth", "owner_url": "https://github.com/google-research", "owner_repos": 359, "owner_followers": 17076, "owner_bio": "", "affiliated_org": "Google DeepMind", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2103.15691", "slug": "vivit-a-video-vision-transformer", "title": "ViViT: A Video Vision Transformer", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "datawhalechina/every-embodied", "slug": "datawhalechina-every-embodied", "url": "https://github.com/datawhalechina/every-embodied", "owner": "datawhalechina", "name": "every-embodied", "description": "\u4ec5\u9700Python\u57fa\u7840\uff0c\u4ece0\u6784\u5efa\u81ea\u5df1\u7684\u5177\u8eab\u667a\u80fd\u673a\u5668\u4eba\uff1b\u4ece0\u9010\u6b65\u6784\u5efaVLA/OpenVLA/SmolVLA/Pi0\uff0c \u6df1\u5165\u7406\u89e3\u5177\u8eab\u667a\u80fd", "readme": "", "stars": 3359, "stars_scraped": 3300, "forks": 340, "watchers": 21, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "embodied-agent", "embodied-ai", "embodied-intelligence", "openvla", "smolvla", "vision-language-action-model" ], "pushed_at": "2026-08-24", "created_at": "2024-12-08", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Datawhale", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/datawhalechina", "owner_repos": 219, "owner_followers": 32136, "owner_bio": "for the learner\uff0c\u548c\u5b66\u4e60\u8005\u4e00\u8d77\u6210\u957f", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "mani-skill/ManiSkill", "slug": "mani-skill-maniskill", "url": "https://github.com/mani-skill/ManiSkill", "owner": "mani-skill", "name": "ManiSkill", "description": "Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark", "readme": "", "stars": 3264, "stars_scraped": 3300, "forks": 535, "watchers": 21, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "embodied-ai", "reinforcement-learning", "robot-learning", "robot-manipulation", "robotics", "simulation" ], "pushed_at": "2026-08-04", "created_at": "2022-08-02", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "ManiSkill", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/mani-skill", "owner_repos": 2, "owner_followers": 16, "owner_bio": "Community for developing the ManiSkill robotics simulation framework and related tools", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "OpenDriveLab/AgiBot-World", "slug": "opendrivelab-agibot-world", "url": "https://github.com/OpenDriveLab/AgiBot-World", "owner": "OpenDriveLab", "name": "AgiBot-World", "description": "[IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems", "readme": "", "stars": 3157, "stars_scraped": 3200, "forks": 217, "watchers": 37, "language": null, "license": null, "gh_topics": [ "pretraining-for-robotics", "robotic-foundation-model", "robotic-manipulation", "vision-language-action-model" ], "pushed_at": "2026-05-29", "created_at": "", "archived": false, "paper_ids": [ "2503.06669" ], "owner_type": "Organization", "owner_display": "OpenDriveLab", "owner_company": "", "owner_location": "Hong Kong", "owner_url": "https://github.com/OpenDriveLab", "owner_repos": 54, "owner_followers": 2675, "owner_bio": "AI for Robotics and Autonomous Driving at The University of Hong Kong (HKU)", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2503.06669", "slug": "agibot-world-colosseo-a-large-scale-manipulation-platform-for-scalable", "title": "AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems", "featured": false } ], "topics": [ "vla", "foundation-pretraining" ], "score": 6, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "facebookresearch/habitat-lab", "slug": "facebookresearch-habitat-lab", "url": "https://github.com/facebookresearch/habitat-lab", "owner": "facebookresearch", "name": "habitat-lab", "description": "A modular high-level library to train embodied AI agents across a variety of tasks and environments.", "readme": "", "stars": 3108, "stars_scraped": 3100, "forks": 687, "watchers": 43, "language": "Python", "license": "MIT", "gh_topics": [ "ai", "computer-vision", "deep-learning", "deep-reinforcement-learning", "python", "reinforcement-learning", "research", "robotics", "sim2real", "simulator" ], "pushed_at": "2026-05-07", "created_at": "2019-02-04", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Meta Research", "owner_company": "", "owner_location": "Menlo Park, California", "owner_url": "https://github.com/facebookresearch", "owner_repos": 1436, "owner_followers": 37143, "owner_bio": "", "affiliated_org": "Meta FAIR", "link_sources": [], "papers": [], "topics": [ "sim2real" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "enactic/openarm", "slug": "enactic-openarm", "url": "https://github.com/enactic/openarm", "owner": "enactic", "name": "openarm", "description": "A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.", "readme": "OpenArm Cell (on the right) is a standardized environment with unified background, lighting, and camera placement. Research performed using OpenArm can be reproduced around the world in consistent evaluation conditions, facilitating the global discussion on state of the art physical AI research.", "stars": 2889, "stars_scraped": 2900, "forks": 319, "watchers": 46, "language": "MDX", "license": "Apache-2.0", "gh_topics": [ "bilateral-teleoperation", "force-feedback", "genesis", "gravity-compensation", "humanoid-robot", "imitation-learning", "machine-learning", "moveit2", "mujoco", "open-source", "openarm", "python", "reinforcement-learning", "robot", "robot-arm", "robotics", "ros2", "teleoperation" ], "pushed_at": "2026-08-20", "created_at": "2024-09-29", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Enactic, Inc.", "owner_company": "", "owner_location": "Japan", "owner_url": "https://github.com/enactic", "owner_repos": 51, "owner_followers": 215, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "tactile", "data-teleop" ], "score": 8, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "mujocolab/mjlab", "slug": "mujocolab-mjlab", "url": "https://github.com/mujocolab/mjlab", "owner": "mujocolab", "name": "mjlab", "description": "Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research", "readme": "mjlab combines Isaac Lab 's manager-based API with MuJoCo Warp , a GPU-accelerated version of MuJoCo . The framework provides composable building blocks for environment design, with minimal dependencies and direct access to native MuJoCo data structures.", "stars": 2837, "stars_scraped": 2800, "forks": 501, "watchers": 29, "language": null, "license": null, "gh_topics": [ "isaaclab", "mujoco", "mujoco-warp", "reinforcement-learning", "robotics-simulation" ], "pushed_at": "2026-08-26", "created_at": "", "archived": false, "paper_ids": [ "2601.22074" ], "owner_type": "Organization", "owner_display": "mujocolab", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/mujocolab", "owner_repos": 5, "owner_followers": 234, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2601.22074", "slug": "mjlab-a-lightweight-framework-for-gpu-accelerated-robot-learning", "title": "mjlab: A Lightweight Framework for GPU-Accelerated Robot Learning", "featured": false } ], "topics": [], "score": 6, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "ARISE-Initiative/robosuite", "slug": "arise-initiative-robosuite", "url": "https://github.com/ARISE-Initiative/robosuite", "owner": "ARISE-Initiative", "name": "robosuite", "description": "robosuite: A Modular Simulation Framework and Benchmark for Robot Learning", "readme": "[10/28/2024] v1.5 : Added support for diverse robot embodiments (including humanoids), custom robot composition, composite controllers (including whole body controllers), more teleoperation devices, photo-realistic rendering. [release notes] [documentation]", "stars": 2581, "stars_scraped": 2600, "forks": 760, "watchers": 29, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "physics-simulation", "reinforcement-learning", "robot-learning", "robot-manipulation", "robotics" ], "pushed_at": "2026-07-11", "created_at": "2018-10-25", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "ARISE Initiative", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/ARISE-Initiative", "owner_repos": 9, "owner_followers": 281, "owner_bio": "Advancing Robot Intelligence through Simulated Environments (ARISE)", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real", "data-teleop" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "yifan123/flow_grpo", "slug": "yifan123-flow-grpo", "url": "https://github.com/yifan123/flow_grpo", "owner": "yifan123", "name": "flow_grpo", "description": "[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL", "readme": "2025-11-04", "stars": 2499, "stars_scraped": 2500, "forks": 168, "watchers": 23, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-05-07", "created_at": "", "archived": false, "paper_ids": [ "2505.05470" ], "owner_type": "User", "owner_display": "Jie Liu", "owner_company": "The Chinese University of Hong Kong", "owner_location": "", "owner_url": "https://github.com/yifan123", "owner_repos": 25, "owner_followers": 224, "owner_bio": "Ph.D. student @ MMLab, CUHK", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2505.05470", "slug": "flow-grpo-training-flow-matching-models-via-online-rl", "title": "Flow-GRPO: Training Flow Matching Models via Online RL", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "OpenHelix-Team/VLA-Adapter", "slug": "openhelix-team-vla-adapter", "url": "https://github.com/OpenHelix-Team/VLA-Adapter", "owner": "OpenHelix-Team", "name": "VLA-Adapter", "description": "VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model", "readme": "\ud83d\udcdd Paper: https://arxiv.org/abs/2509.09372 \ud83c\udf0d Project page: https://vla-adapter.github.io/ \ud83e\udd17 HuggingFace: https://huggingface.co/VLA-Adapter Github: https://github.com/OpenHelix-Team/VLA-Adapter", "stars": 2294, "stars_scraped": 2300, "forks": 208, "watchers": 30, "language": "Python", "license": "MIT", "gh_topics": [ "embodied-ai", "robotics", "vision-language-action-model" ], "pushed_at": "2026-03-19", "created_at": "2025-09-20", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "OpenHelix Robotics", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/OpenHelix-Team", "owner_repos": 20, "owner_followers": 261, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "LMD0311/Awesome-World-Model", "slug": "lmd0311-awesome-world-model", "url": "https://github.com/LMD0311/Awesome-World-Model", "owner": "LMD0311", "name": "Awesome-World-Model", "description": "Collect some World Models for Autonomous Driving (and Robotic, etc.) papers. ", "readme": "If you find some ignored papers, feel free to create pull requests , or open issues . Contributions in any form to make this list more comprehensive are welcome. \ud83d\udce3\ud83d\udce3\ud83d\udce3", "stars": 2225, "stars_scraped": 2200, "forks": 86, "watchers": 60, "language": null, "license": null, "gh_topics": [ "artificial-intelligence", "artificial-intelligence-algorithms", "autonomous-driving", "autonomous-vehicles", "awesome", "computer-vision", "deep-learning", "future-predict", "robotics", "world-model" ], "pushed_at": "2026-08-17", "created_at": "2024-01-02", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Xin Zhou", "owner_company": "Huazhong University of Science & Technology", "owner_location": "Wuhan, Hubei Province, China", "owner_url": "https://github.com/LMD0311", "owner_repos": 16, "owner_followers": 111, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "navigation" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "rlworkgroup/garage", "slug": "rlworkgroup-garage", "url": "https://github.com/rlworkgroup/garage", "owner": "rlworkgroup", "name": "garage", "description": "A toolkit for reproducible reinforcement learning research.", "readme": "The toolkit provides wide range of modular tools for implementing RL algorithms, including:", "stars": 2126, "stars_scraped": 2100, "forks": 328, "watchers": 52, "language": null, "license": null, "gh_topics": [ "pytorch", "reproducibility", "rl-algorithms", "tensorflow" ], "pushed_at": "2023-05-04", "created_at": "", "archived": false, "paper_ids": [ "1910.10897" ], "owner_type": "Organization", "owner_display": "Reinforcement Learning Working Group", "owner_company": "", "owner_location": "California, USA", "owner_url": "https://github.com/rlworkgroup", "owner_repos": 9, "owner_followers": 140, "owner_bio": "Coalition of researchers which develop open source reinforcement learning research software", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "1910.10897", "slug": "meta-world-a-benchmark-and-evaluation-for-multi-task-and-meta-reinforc", "title": "Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning", "featured": false } ], "topics": [ "rl-control" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "roboterax/humanoid-gym", "slug": "roboterax-humanoid-gym", "url": "https://github.com/roboterax/humanoid-gym", "owner": "roboterax", "name": "humanoid-gym", "description": "Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695", "readme": "*: Equal contribution. Project Co-lead., \u2020: Corresponding Author.", "stars": 2075, "stars_scraped": 2100, "forks": 254, "watchers": 24, "language": "Python", "license": null, "gh_topics": [ "ai", "artificial-intelligence", "control-systems", "humanoid-robot", "locomotion", "machine-learning", "robotics" ], "pushed_at": "2025-01-26", "created_at": "2024-03-04", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "RobotEra TECHNOLOGY CO.,LTD.", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/roboterax", "owner_repos": 10, "owner_followers": 173, "owner_bio": "Founded in 2023, RobotEra TECHNOLOGY CO., LTD focuses on the R&D of embodied AI general-purpose humanoid robots.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real", "rl-control" ], "score": 9, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "NVlabs/alpamayo", "slug": "nvlabs-alpamayo", "url": "https://github.com/NVlabs/alpamayo", "owner": "NVlabs", "name": "alpamayo", "description": "NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.", "readme": "\ud83d\udc49 Visit the new Alpamayo hub: https://github.com/NVlabs/alpamayo-recipes", "stars": 2005, "stars_scraped": 2000, "forks": 337, "watchers": 47, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "alpamayo", "autonomous-driving", "autonomous-vehicles", "chain-of-causation", "computer-vision", "end-to-end-driving", "nvidia", "physical-ai", "reasoning", "robotics", "self-driving-car", "trajectory-prediction", "vision-language-action", "vla", "world-models" ], "pushed_at": "2026-08-05", "created_at": "2025-11-19", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "NVIDIA Research Projects", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/NVlabs", "owner_repos": 500, "owner_followers": 11191, "owner_bio": "", "affiliated_org": "NVIDIA", "link_sources": [], "papers": [], "topics": [ "world-models", "vla" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "LTH14/mar", "slug": "lth14-mar", "url": "https://github.com/LTH14/mar", "owner": "LTH14", "name": "mar", "description": "PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838", "readme": "This is a PyTorch/GPU implementation of the paper Autoregressive Image Generation without Vector Quantization (Neurips 2024 Spotlight Presentation):", "stars": 1949, "stars_scraped": 2000, "forks": 124, "watchers": 18, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-02-20", "created_at": "", "archived": false, "paper_ids": [ "2406.11838" ], "owner_type": "User", "owner_display": "Tianhong Li", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/LTH14", "owner_repos": 11, "owner_followers": 931, "owner_bio": "I'm a postdoc at MIT. My recent research interests are generative models and representation learning.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2406.11838", "slug": "autoregressive-image-generation-without-vector-quantization", "title": "Autoregressive Image Generation without Vector Quantization", "featured": false } ], "topics": [ "video-generation" ], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "leofan90/Awesome-World-Models", "slug": "leofan90-awesome-world-models", "url": "https://github.com/leofan90/Awesome-World-Models", "owner": "leofan90", "name": "Awesome-World-Models", "description": "A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related websites.", "readme": "Maintainers can use the arXiv candidate pipeline to discover recent papers for review.", "stars": 1985, "stars_scraped": 2000, "forks": 74, "watchers": 39, "language": "Python", "license": "BSD-3-Clause", "gh_topics": [ "artificial-intelligence", "autonomous-driving", "awesome", "deep-learning", "embodied-ai", "future-prediction", "video-prediction", "world-model" ], "pushed_at": "2026-08-26", "created_at": "2024-11-09", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Leo Fan", "owner_company": "PKU", "owner_location": "", "owner_url": "https://github.com/leofan90", "owner_repos": 4, "owner_followers": 23, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "navigation", "video-generation" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Farama-Foundation/Metaworld", "slug": "farama-foundation-metaworld", "url": "https://github.com/Farama-Foundation/Metaworld", "owner": "Farama-Foundation", "name": "Metaworld", "description": "Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning", "readme": "Meta-World is an open source benchmark for developing and evaluating multi-task and meta reinforcement learning algorithms for continuous control robotic manipulation environments, with various benchmarks to evaluate different aspects of reinforcement learning algorithms.", "stars": 1871, "stars_scraped": 1900, "forks": 351, "watchers": 28, "language": null, "license": null, "gh_topics": [ "benchmark-environments", "meta-rl", "mujoco", "multi-task" ], "pushed_at": "2026-08-10", "created_at": "", "archived": false, "paper_ids": [ "1910.10897" ], "owner_type": "Organization", "owner_display": "Farama Foundation", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Farama-Foundation", "owner_repos": 45, "owner_followers": 2010, "owner_bio": "Maintaining the World's Open Source Reinforcement Learning Tools", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "1910.10897", "slug": "meta-world-a-benchmark-and-evaluation-for-multi-task-and-meta-reinforc", "title": "Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning", "featured": false } ], "topics": [ "rl-control" ], "score": 3, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "showlab/ShowUI", "slug": "showlab-showui", "url": "https://github.com/showlab/ShowUI", "owner": "showlab", "name": "ShowUI", "description": "[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.", "readme": "", "stars": 1893, "stars_scraped": 1900, "forks": 141, "watchers": 19, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "agent", "computer-use", "gui-agent", "vision-language-action", "vision-language-model" ], "pushed_at": "2026-04-24", "created_at": "2024-10-31", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Show Lab", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/showlab", "owner_repos": 139, "owner_followers": 1209, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Thinklab-SJTU/Awesome-LLM4AD", "slug": "thinklab-sjtu-awesome-llm4ad", "url": "https://github.com/Thinklab-SJTU/Awesome-LLM4AD", "owner": "Thinklab-SJTU", "name": "Awesome-LLM4AD", "description": "A curated list of awesome LLM/VLM/VLA/World Model for Autonomous Driving(LLM4AD) resources (continually updated)", "readme": "", "stars": 1892, "stars_scraped": 1900, "forks": 112, "watchers": 49, "language": null, "license": "Apache-2.0", "gh_topics": [ "large-language-models", "vision-language-action-model", "vision-language-model", "world-model" ], "pushed_at": "2026-06-22", "created_at": "2023-10-06", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Thinklab (SJTU & SII)", "owner_company": "", "owner_location": "Shanghai", "owner_url": "https://github.com/Thinklab-SJTU", "owner_repos": 83, "owner_followers": 853, "owner_bio": "ReThinklab at Shanghai Jiao Tong University and SII, focusing on machine learning and applications, led by Prof. Junchi Yan.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "navigation" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "zchoi/Awesome-Embodied-Robotics-and-Agent", "slug": "zchoi-awesome-embodied-robotics-and-agent", "url": "https://github.com/zchoi/Awesome-Embodied-Robotics-and-Agent", "owner": "zchoi", "name": "Awesome-Embodied-Robotics-and-Agent", "description": "This is a curated list of \"Embodied AI or robot with Large Language Models\" research. Watch this repository for the latest updates! \ud83d\udd25", "readme": "[2026/05/11] \ud83c\udf89 Add NavSpace: How Intelligent Agents Follow Spatial Intelligence Instructions ( ICRA 2026 ), the first benchmark for evaluating spatial intelligence in embodied navigation, with open-sourced dataset, evaluation code, and baseline SNav . [arXiv] [Github] [2025/10/30] \ud83c\udf89 Our survey paper \" A Survey on Efficient Vision-Language-Action Models \" [arXiv] has been released! [2025/04/23] Add", "stars": 1858, "stars_scraped": 1900, "forks": 97, "watchers": 47, "language": null, "license": "Apache-2.0", "gh_topics": [ "agent", "awesome", "embodied-agent", "embodied-ai", "large-language-model", "manipulator-robotics", "navigation", "planning-algorithms", "scene-understanding" ], "pushed_at": "2026-08-14", "created_at": "2023-07-19", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Haonan Zhang", "owner_company": "UESTC | UniTn", "owner_location": "Sichuan \u21cc Italy", "owner_url": "https://github.com/zchoi", "owner_repos": 20, "owner_followers": 108, "owner_bio": "Ph.D. student. Research Interests: LLM-Agents, Vision-Language.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "navigation" ], "score": 10, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "baaivision/Emu", "slug": "baaivision-emu", "url": "https://github.com/baaivision/Emu", "owner": "baaivision", "name": "Emu", "description": "Emu Series: Generative Multimodal Models from BAAI", "readme": "Emu3 (arXiv 2024, 2024/09) - Next-Token Prediction is All You Need \ud83d\udd25\ud83d\udd25\ud83d\udd25", "stars": 1778, "stars_scraped": 1800, "forks": 83, "watchers": 21, "language": null, "license": null, "gh_topics": [ "foundation-models", "generative-pretraining-in-multimodality", "in-context-learning", "instruct-tuning", "multimodal-generalist", "multimodal-pretraining" ], "pushed_at": "2026-01-12", "created_at": "", "archived": false, "paper_ids": [ "2307.05222" ], "owner_type": "Organization", "owner_display": "BAAI-Vision", "owner_company": "", "owner_location": "China", "owner_url": "https://github.com/baaivision", "owner_repos": 22, "owner_followers": 771, "owner_bio": "Foundation model fanatics from BAAI.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2307.05222", "slug": "emu-generative-pretraining-in-multimodality", "title": "Emu: Generative Pretraining in Multimodality", "featured": false } ], "topics": [ "foundation-pretraining" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "qiayuanl/legged_control", "slug": "qiayuanl-legged-control", "url": "https://github.com/qiayuanl/legged_control", "owner": "qiayuanl", "name": "legged_control", "description": "NMPC, WBC, state estimation, and sim2real framework for legged robots based on OCS2 and ros-controls", "readme": "Note", "stars": 1793, "stars_scraped": 1800, "forks": 361, "watchers": 18, "language": "C++", "license": "BSD-3-Clause", "gh_topics": [], "pushed_at": "2025-02-13", "created_at": "2022-06-24", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Qiayuan Liao", "owner_company": "UC Berkeley", "owner_location": "Berkeley", "owner_url": "https://github.com/qiayuanl", "owner_repos": 50, "owner_followers": 1268, "owner_bio": "", "affiliated_org": "UC Berkeley", "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real" ], "score": 8, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "Robbyant/lingbot-vla", "slug": "robbyant-lingbot-vla", "url": "https://github.com/Robbyant/lingbot-vla", "owner": "Robbyant", "name": "lingbot-vla", "description": "A Pragmatic VLA Foundation Model", "readme": "LingBot-VLA has focused on being Pragmatic :", "stars": 1777, "stars_scraped": 1800, "forks": 183, "watchers": 11, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "embodied-ai", "vla" ], "pushed_at": "2026-06-11", "created_at": "2026-01-26", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Robbyant", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Robbyant", "owner_repos": 10, "owner_followers": 1495, "owner_bio": "Intelligence in Action, Benefits for Everyone", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "foundation-pretraining" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Vchitect/VBench", "slug": "vchitect-vbench", "url": "https://github.com/Vchitect/VBench", "owner": "Vchitect", "name": "VBench", "description": "[CVPR2024 Highlight] VBench - We Evaluate Video Generation", "readme": "This repository provides unified implementations for the VBench series of works, supporting comprehensive evaluation of video generative models across a wide spectrum of capabilities and settings.", "stars": 1747, "stars_scraped": 1700, "forks": 132, "watchers": 16, "language": null, "license": null, "gh_topics": [ "aigc", "benchmark", "dataset", "evaluation-kit", "gen-ai", "stable-diffusion", "text-to-video", "video-generation" ], "pushed_at": "2026-08-21", "created_at": "", "archived": false, "paper_ids": [ "2311.17982", "2503.21755" ], "owner_type": "Organization", "owner_display": "Vchitect", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Vchitect", "owner_repos": 37, "owner_followers": 484, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2311.17982", "slug": "vbench-comprehensive-benchmark-suite-for-video-generative-models", "title": "VBench: Comprehensive Benchmark Suite for Video Generative Models", "featured": false }, { "id": "2503.21755", "slug": "vbench-2-0-advancing-video-generation-benchmark-suite-for-intrinsic-fa", "title": "VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness", "featured": false } ], "topics": [ "video-generation" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "unitreerobotics/xr_teleoperate", "slug": "unitreerobotics-xr-teleoperate", "url": "https://github.com/unitreerobotics/xr_teleoperate", "owner": "unitreerobotics", "name": "xr_teleoperate", "description": "This repository implements teleoperation of the Unitree humanoid robot using XR Devices.", "readme": "", "stars": 1633, "stars_scraped": 1600, "forks": 325, "watchers": 20, "language": "Python", "license": "NOASSERTION", "gh_topics": [], "pushed_at": "2026-08-03", "created_at": "2024-08-05", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Unitree Robotics", "owner_company": "", "owner_location": "Hangzhou China", "owner_url": "https://github.com/unitreerobotics", "owner_repos": 53, "owner_followers": 6772, "owner_bio": "High performance civilian robot manufacturer. Please everyone be sure to use the robot in a Friendly and Safe manner.", "affiliated_org": "Unitree", "link_sources": [], "papers": [], "topics": [ "humanoids", "data-teleop" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Zhefan-Xu/NavRL", "slug": "zhefan-xu-navrl", "url": "https://github.com/Zhefan-Xu/NavRL", "owner": "Zhefan-Xu", "name": "NavRL", "description": "[IEEE RA-L'25] NavRL: Learning Safe Flight in Dynamic Environments (NVIDIA Isaac/Python/ROS1/ROS2)", "readme": "For additional details, please refer to the related paper available here:", "stars": 1587, "stars_scraped": 1600, "forks": 168, "watchers": 9, "language": "C++", "license": "MIT", "gh_topics": [ "collision-avoidance", "embodied-ai", "isaac-sim", "nvidia-isaac", "reinforcement-learning", "robot-navigation", "robotics", "ros1-noetic", "ros2-humble" ], "pushed_at": "2025-07-03", "created_at": "2025-02-12", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Zhefan Xu", "owner_company": "Carnegie Mellon University", "owner_location": "Pittsburgh, PA, US", "owner_url": "https://github.com/Zhefan-Xu", "owner_repos": 76, "owner_followers": 852, "owner_bio": "PhD @ CMU | ex-Waymo, ex-Cruise | Robotics & AI", "affiliated_org": "CMU", "link_sources": [], "papers": [], "topics": [ "navigation" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "Tencent-Hunyuan/HY-WorldPlay", "slug": "tencent-hunyuan-hy-worldplay", "url": "https://github.com/Tencent-Hunyuan/HY-WorldPlay", "owner": "Tencent-Hunyuan", "name": "HY-WorldPlay", "description": "HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency", "readme": "Join our Wechat and Discord group to discuss and find help from us.", "stars": 1586, "stars_scraped": 1600, "forks": 143, "watchers": 13, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "3d", "hunyuan", "hunyuan-world", "hunyuan3d", "image-to-3d", "world-model", "world-models" ], "pushed_at": "2026-06-10", "created_at": "2025-12-10", "archived": false, "paper_ids": [ "2512.14614" ], "owner_type": "Organization", "owner_display": "Tencent-Hunyuan", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Tencent-Hunyuan", "owner_repos": 79, "owner_followers": 3204, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2512.14614", "slug": "worldplay-towards-long-term-geometric-consistency-for-real-time-intera", "title": "WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling", "featured": false } ], "topics": [ "world-models" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "Improbable-AI/walk-these-ways", "slug": "improbable-ai-walk-these-ways", "url": "https://github.com/Improbable-AI/walk-these-ways", "owner": "Improbable-AI", "name": "walk-these-ways", "description": "Sim-to-real RL training and deployment tools for the Unitree Go1 robot.", "readme": "This environment builds on the legged gym environment by Nikita Rudin, Robotic Systems Lab, ETH Zurich (Paper: https://arxiv.org/abs/2109.11978 ) and the Isaac Gym simulator from NVIDIA (Paper: https://arxiv.org/abs/2108.10470 ). Training code builds on the rsl_rl repository, also by Nikita Rudin, Robotic Systems Lab, ETH Zurich. All redistributed code retains its original license .", "stars": 1438, "stars_scraped": 1400, "forks": 222, "watchers": 14, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "go1", "reinforcement-learning", "robotics", "sim-to-real", "unitree" ], "pushed_at": "2024-06-16", "created_at": "2022-11-15", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Improbable-AI @MIT", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Improbable-AI", "owner_repos": 47, "owner_followers": 266, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real" ], "score": 8, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "apple/ml-aim", "slug": "apple-ml-aim", "url": "https://github.com/apple/ml-aim", "owner": "apple", "name": "ml-aim", "description": "This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.", "readme": "If you're looking for the original AIM model (AIMv1), please refer to the README here .", "stars": 1424, "stars_scraped": 1400, "forks": 73, "watchers": 26, "language": null, "license": null, "gh_topics": [ "jax", "large-scale-vision-models", "mlx", "pytorch" ], "pushed_at": "2025-08-04", "created_at": "", "archived": false, "paper_ids": [ "2401.08541" ], "owner_type": "Organization", "owner_display": "Apple", "owner_company": "", "owner_location": "Cupertino, CA", "owner_url": "https://github.com/apple", "owner_repos": 441, "owner_followers": 39692, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2401.08541", "slug": "scalable-pre-training-of-large-autoregressive-image-models", "title": "Scalable Pre-training of Large Autoregressive Image Models", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "reiniscimurs/DRL-robot-navigation", "slug": "reiniscimurs-drl-robot-navigation", "url": "https://github.com/reiniscimurs/DRL-robot-navigation", "owner": "reiniscimurs", "name": "DRL-robot-navigation", "description": "Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic Policy Gradient (TD3) neural network, a robot learns to navigate to a random goal point in a simulated environment while avoiding obstacles.", "readme": "Installation and code overview tutorial available here", "stars": 1356, "stars_scraped": 1400, "forks": 193, "watchers": 11, "language": "Python", "license": "MIT", "gh_topics": [ "deep-learning", "deep-reinforcement-learning", "gazebo", "obstacle-avoidance", "obstacle-avoidance-robot", "reinforcement-learning", "robot-navigation", "ros", "td3" ], "pushed_at": "2025-12-13", "created_at": "2021-10-25", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Reinis Cimurs", "owner_company": "", "owner_location": "Stuttgart, Germany", "owner_url": "https://github.com/reiniscimurs", "owner_repos": 17, "owner_followers": 195, "owner_bio": "ireinisi@gmail.com", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real", "rl-control", "navigation" ], "score": 11, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "thu-ml/Motus", "slug": "thu-ml-motus", "url": "https://github.com/thu-ml/Motus", "owner": "thu-ml", "name": "Motus", "description": "Official code of Motus: A Unified Latent Action World Model", "readme": "We welcome community members to help maintain and extend Motus. Welcome to join the Motus community and contribute together!", "stars": 1246, "stars_scraped": 1200, "forks": 73, "watchers": 8, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "diffusion-model", "robotic-manipulation", "robotics", "unidiffuser", "video-generation", "vision-language-action-model", "world-model" ], "pushed_at": "2026-01-05", "created_at": "2025-12-12", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "TSAIL group", "owner_company": "", "owner_location": "FIT Building, Tsinghua University, Beijing, China", "owner_url": "https://github.com/thu-ml", "owner_repos": 93, "owner_followers": 1781, "owner_bio": "Tsinghua Statistical Artificial Intelligence & Learning Group", "affiliated_org": "Tsinghua", "link_sources": [], "papers": [], "topics": [ "world-models", "vla" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "X-Square-Robot/wall-x", "slug": "x-square-robot-wall-x", "url": "https://github.com/X-Square-Robot/wall-x", "owner": "X-Square-Robot", "name": "wall-x", "description": "Building General-Purpose Robots Based on Embodied Foundation Model", "readme": "This repository provides the training and inference code for the WALL series open-source embodied foundation models. It includes LeRobot data preparation, model configuration, flow-matching and FAST action branches, public serving and evaluation utilities, and exported CUDA operator sources that compile during package installation.", "stars": 1236, "stars_scraped": 1200, "forks": 98, "watchers": 13, "language": "Python", "license": "Apache-2.0", "gh_topics": [], "pushed_at": "2026-08-18", "created_at": "2025-09-04", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "X Square Robot", "owner_company": "", "owner_location": "China", "owner_url": "https://github.com/X-Square-Robot", "owner_repos": 13, "owner_followers": 200, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "foundation-pretraining" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "OpenDriveLab/UniVLA", "slug": "opendrivelab-univla", "url": "https://github.com/OpenDriveLab/UniVLA", "owner": "OpenDriveLab", "name": "UniVLA", "description": "[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions", "readme": "", "stars": 1124, "stars_scraped": 1100, "forks": 69, "watchers": 8, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "robot-learning", "vision-language-actions-models", "vla" ], "pushed_at": "2025-11-19", "created_at": "2025-04-23", "archived": false, "paper_ids": [ "2505.06111" ], "owner_type": "Organization", "owner_display": "OpenDriveLab", "owner_company": "", "owner_location": "Hong Kong", "owner_url": "https://github.com/OpenDriveLab", "owner_repos": 54, "owner_followers": 2675, "owner_bio": "AI for Robotics and Autonomous Driving at The University of Hong Kong (HKU)", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2505.06111", "slug": "univla-learning-to-act-anywhere-with-task-centric-latent-actions", "title": "UniVLA: Learning to Act Anywhere with Task-centric Latent Actions", "featured": false } ], "topics": [ "vla" ], "score": 3, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "hanruihua/ir-sim", "slug": "hanruihua-ir-sim", "url": "https://github.com/hanruihua/ir-sim", "owner": "hanruihua", "name": "ir-sim", "description": "A Python-based lightweight robot simulator designed for navigation, control, and learning", "readme": "IR-SIM is an open-source, Python-based, lightweight robot simulator designed for navigation, control, and learning. It provides a simple, user-friendly framework with built-in collision detection for modeling robots, sensors, and environments. Ideal for academic and educational use, IR-SIM enables rapid prototyping of robotics and learning algorithms in custom scenarios with minimal coding and har", "stars": 1119, "stars_scraped": 1100, "forks": 143, "watchers": 10, "language": "Python", "license": "MIT", "gh_topics": [ "autonomous-driving", "control", "ir-sim", "multi-agent", "navigation", "path-planning", "python", "reinforcement-learning", "robotics", "robotics-simulation", "simulator" ], "pushed_at": "2026-08-26", "created_at": "2022-05-30", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "hanruihua", "owner_company": "HKU", "owner_location": "Hong Kong", "owner_url": "https://github.com/hanruihua", "owner_repos": 57, "owner_followers": 450, "owner_bio": "Postdoc, Ph.D. @ HKU", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real", "navigation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "andyzeng/visual-pushing-grasping", "slug": "andyzeng-visual-pushing-grasping", "url": "https://github.com/andyzeng/visual-pushing-grasping", "owner": "andyzeng", "name": "visual-pushing-grasping", "description": "Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.", "readme": "", "stars": 1109, "stars_scraped": 1100, "forks": 328, "watchers": 30, "language": "Python", "license": "BSD-2-Clause", "gh_topics": [ "3d", "artificial-intelligence", "computer-vision", "deep-learning", "deep-reinforcement-learning", "grasping", "manipulation", "pushing", "robotics", "vision" ], "pushed_at": "2021-05-11", "created_at": "2018-04-05", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Andy Zeng", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/andyzeng", "owner_repos": 9, "owner_followers": 1671, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "dexterous-manipulation", "rl-control" ], "score": 6, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "nicrusso7/rex-gym", "slug": "nicrusso7-rex-gym", "url": "https://github.com/nicrusso7/rex-gym", "owner": "nicrusso7", "name": "rex-gym", "description": "OpenAI Gym environments for an open-source quadruped robot (SpotMicro)", "readme": "This project is mostly inspired by the incredible works done by Boston Dynamics.", "stars": 1102, "stars_scraped": 1100, "forks": 140, "watchers": 38, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "artificial-intelligence", "gym-environment", "inverse-kinematics", "legged-robots", "machine-learning", "openai", "openai-gym", "openai-gym-environments", "pybullet", "python3", "quadruped", "quadruped-robot", "quadruped-robot-gaits", "reinforcement-learning", "reinforcement-learning-algorithms", "robot", "robotic-arm", "robotics", "spotmicro", "tensorflow" ], "pushed_at": "2023-03-24", "created_at": "2019-10-27", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Nicola Russo", "owner_company": "", "owner_location": "Milano, Italy", "owner_url": "https://github.com/nicrusso7", "owner_repos": 13, "owner_followers": 83, "owner_bio": "Every problem has a solution.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "BaiShuanghao/Awesome-Robotics-Manipulation", "slug": "baishuanghao-awesome-robotics-manipulation", "url": "https://github.com/BaiShuanghao/Awesome-Robotics-Manipulation", "owner": "BaiShuanghao", "name": "Awesome-Robotics-Manipulation", "description": "A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.", "readme": "", "stars": 1098, "stars_scraped": 1100, "forks": 62, "watchers": 17, "language": null, "license": "MIT", "gh_topics": [ "diffusion-policy", "grasping", "imitation-learning", "input-modeling", "latent-learning", "policy-learning", "robot-manipulation", "vision-language-action-model" ], "pushed_at": "2026-08-25", "created_at": "2024-10-23", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Bai Shuanghao", "owner_company": "Xi'an Jiaotong University", "owner_location": "Xi'an, China", "owner_url": "https://github.com/BaiShuanghao", "owner_repos": 8, "owner_followers": 75, "owner_bio": "Ph.D student @ Xi'an Jiaotong University", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "dexterous-manipulation" ], "score": 10, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Toni-SM/skrl", "slug": "toni-sm-skrl", "url": "https://github.com/Toni-SM/skrl", "owner": "Toni-SM", "name": "skrl", "description": "Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments", "readme": "Documentation: https://skrl.readthedocs.io", "stars": 1089, "stars_scraped": 1100, "forks": 155, "watchers": 8, "language": "Python", "license": "MIT", "gh_topics": [ "brax", "deep-learning", "flax", "gym", "gymnasium", "isaaclab", "isaacsim", "jax", "machine-learning", "multi-agent", "python", "reinforcement-learning", "robotics", "torch", "warp" ], "pushed_at": "2026-05-11", "created_at": "2021-10-18", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Toni-SM", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Toni-SM", "owner_repos": 19, "owner_followers": 153, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "rl-control" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "silvery107/rl-mpc-locomotion", "slug": "silvery107-rl-mpc-locomotion", "url": "https://github.com/silvery107/rl-mpc-locomotion", "owner": "silvery107", "name": "rl-mpc-locomotion", "description": "Deep RL for MPC control of Quadruped Robot Locomotion", "readme": "The RL training utilizes the NVIDIA Isaac Gym in parallel using Unitree Robotics Aliengo model, and transferring it from simulation to reality on a real Aliengo robot (sim2real is not included in this codebase).", "stars": 1020, "stars_scraped": 1000, "forks": 92, "watchers": 4, "language": "Python", "license": "MIT", "gh_topics": [ "isaac-gym", "mpc", "quadruped", "reinforcement-learning", "robotics" ], "pushed_at": "2026-04-26", "created_at": "2021-11-22", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Yulun Zhuang", "owner_company": "University of Michigan", "owner_location": "Ann Arbor, MI, US", "owner_url": "https://github.com/silvery107", "owner_repos": 41, "owner_followers": 283, "owner_bio": "PhD Candidate @ UMich Robotics", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real" ], "score": 10, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "kakaobrain/rq-vae-transformer", "slug": "kakaobrain-rq-vae-transformer", "url": "https://github.com/kakaobrain/rq-vae-transformer", "owner": "kakaobrain", "name": "rq-vae-transformer", "description": "The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)", "readme": "The examples of generated images by RQ-Transformer using class conditions and text conditions. Note that the text conditions of the examples are not used in training time.", "stars": 1030, "stars_scraped": 1000, "forks": 114, "watchers": 13, "language": null, "license": null, "gh_topics": [], "pushed_at": "2024-01-03", "created_at": "", "archived": false, "paper_ids": [ "2203.01941" ], "owner_type": "Organization", "owner_display": "kakaobrain", "owner_company": "", "owner_location": "Pankyo, Seongnam, Kyungki, Republic of Korea", "owner_url": "https://github.com/kakaobrain", "owner_repos": 40, "owner_followers": 508, "owner_bio": "Kakao Brain Corp.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2203.01941", "slug": "autoregressive-image-generation-using-residual-quantization", "title": "Autoregressive Image Generation using Residual Quantization", "featured": false } ], "topics": [ "video-generation" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "LeCAR-Lab/dial-mpc", "slug": "lecar-lab-dial-mpc", "url": "https://github.com/LeCAR-Lab/dial-mpc", "owner": "LeCAR-Lab", "name": "dial-mpc", "description": "Official implementation for the paper \"Full-Order Sampling-Based MPC for Torque-Level Locomotion Control via Diffusion-Style Annealing\". DIAL-MPC is a novel sampling-based MPC framework for legged robot full-order torque-level control with both precision and agility in a training-free manner.", "readme": "", "stars": 995, "stars_scraped": 994, "forks": 105, "watchers": 15, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "diffusion", "humanoid", "legged-robots", "mpc", "online-control", "optimal-control", "quadruped", "sampling-based-control" ], "pushed_at": "2025-05-28", "created_at": "2024-09-15", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "LeCAR Lab at CMU", "owner_company": "", "owner_location": "United States of America", "owner_url": "https://github.com/LeCAR-Lab", "owner_repos": 28, "owner_followers": 872, "owner_bio": "Learning and Control for Agile Robotics Lab at CMU", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 7, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "mees/calvin", "slug": "mees-calvin", "url": "https://github.com/mees/calvin", "owner": "mees", "name": "calvin", "description": "CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks", "readme": "Oier Mees , Lukas Hermann , Erick Rosete , Wolfram Burgard", "stars": 972, "stars_scraped": 971, "forks": 124, "watchers": 7, "language": "Python", "license": "MIT", "gh_topics": [ "computer-vision", "deep-learning", "grounding", "manipulation", "natural-language-processing", "pytorch", "robotics", "vision", "vision-and-language", "vision-language" ], "pushed_at": "2025-09-08", "created_at": "2021-07-20", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Oier Mees", "owner_company": "", "owner_location": "Berkeley, CA", "owner_url": "https://github.com/mees", "owner_repos": 45, "owner_followers": 162, "owner_bio": "Postdoc at BAIR/RAIL Lab. Researcher in Machine Learning and Robotics.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "worldbench/awesome-3d-4d-world-models", "slug": "worldbench-awesome-3d-4d-world-models", "url": "https://github.com/worldbench/awesome-3d-4d-world-models", "owner": "worldbench", "name": "awesome-3d-4d-world-models", "description": "[TPAMI 2026] 3D and 4D World Modeling: A Survey", "readme": "We unify terminology, scope, and evaluations, and organize the space into three complementary paradigms by representation:", "stars": 971, "stars_scraped": 971, "forks": 56, "watchers": 27, "language": "HTML", "license": "Apache-2.0", "gh_topics": [ "3d", "3d-generation", "4d", "4d-generation", "autonomous-driving", "awesome-list", "embodied-ai", "lidar-generation", "occupancy-generation", "spatial-intelligence", "video-generation", "world-models" ], "pushed_at": "2026-08-21", "created_at": "2025-06-20", "archived": false, "paper_ids": [ "2509.07996" ], "owner_type": "Organization", "owner_display": "worldbench", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/worldbench", "owner_repos": 29, "owner_followers": 148, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2509.07996", "slug": "3d-and-4d-world-modeling-a-survey", "title": "3D and 4D World Modeling: A Survey", "featured": false } ], "topics": [ "world-models", "spatial-3d" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "StanfordVL/GibsonEnv", "slug": "stanfordvl-gibsonenv", "url": "https://github.com/StanfordVL/GibsonEnv", "owner": "StanfordVL", "name": "GibsonEnv", "description": "Gibson Environments: Real-World Perception for Embodied Agents", "readme": "Summary : Perception and being active (i.e. having a certain level of motion freedom) are closely tied. Learning active perception and sensorimotor control in the physical world is cumbersome as existing algorithms are too slow to efficiently learn in real-time and robots are fragile and costly. This has given a fruitful rise to learning in the simulation which consequently casts a question on tra", "stars": 946, "stars_scraped": 946, "forks": 150, "watchers": 27, "language": "C", "license": "MIT", "gh_topics": [ "computer-vision", "cvpr2018", "deep-learning", "deep-reinforcement-learning", "reinforcement-learning", "research", "robotics", "ros", "sim2real", "simulator" ], "pushed_at": "2024-04-15", "created_at": "2017-12-18", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Stanford Vision and Learning Lab", "owner_company": "", "owner_location": "Stanford, CA", "owner_url": "https://github.com/StanfordVL", "owner_repos": 98, "owner_followers": 622, "owner_bio": "Research Codebase", "affiliated_org": "Stanford", "link_sources": [], "papers": [], "topics": [ "sim2real" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "OpenQuadruped/spot_mini_mini", "slug": "openquadruped-spot-mini-mini", "url": "https://github.com/OpenQuadruped/spot_mini_mini", "owner": "OpenQuadruped", "name": "spot_mini_mini", "description": "Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion.", "readme": "", "stars": 941, "stars_scraped": 939, "forks": 193, "watchers": 40, "language": "C++", "license": "MIT", "gh_topics": [ "control", "environment", "gait", "gym-environment", "locomotion", "machine-learning", "open-source", "openai-gym", "openai-gym-environments", "optimization", "pybullet", "quadruped", "quadruped-robot", "quadruped-robot-gaits", "quadruped-robots", "reinforcement-learning", "ros", "spot", "terrain", "walker" ], "pushed_at": "2022-10-05", "created_at": "2020-03-31", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "OpenQuadruped", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/OpenQuadruped", "owner_repos": 2, "owner_followers": 40, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real" ], "score": 10, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "mbreuss/diffusion-literature-for-robotics", "slug": "mbreuss-diffusion-literature-for-robotics", "url": "https://github.com/mbreuss/diffusion-literature-for-robotics", "owner": "mbreuss", "name": "diffusion-literature-for-robotics", "description": "Summary of key papers and blogs about diffusion models to learn about the topic. Detailed list of all published diffusion robotics papers.", "readme": "This repository offers a brief summary of essential papers and blogs on diffusion models, alongside a categorized collection of robotics diffusion papers and useful code repositories for starting your own diffusion robotics project.", "stars": 919, "stars_scraped": 919, "forks": 44, "watchers": 29, "language": null, "license": "MIT", "gh_topics": [ "diffusion-models", "grasping", "grasping-robot", "imitation-learning", "literature", "motion-planning", "offline-rl", "reinforcement-learning", "robotics", "score-based-generative-modeling", "summary", "video-diffusion-model" ], "pushed_at": "2024-09-20", "created_at": "2022-11-02", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Moritz Reuss", "owner_company": "", "owner_location": "Karlsruhe, Germany", "owner_url": "https://github.com/mbreuss", "owner_repos": 14, "owner_followers": 112, "owner_bio": "PhD Student @ KIT working on robot learning", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "dexterous-manipulation", "video-generation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "OpenDriveLab/Vista", "slug": "opendrivelab-vista", "url": "https://github.com/OpenDriveLab/Vista", "owner": "OpenDriveLab", "name": "Vista", "description": "[NeurIPS 2024] A Generalizable World Model for Autonomous Driving", "readme": "The official implementation of our NeurIPS 2024 paper:", "stars": 895, "stars_scraped": 895, "forks": 61, "watchers": 18, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "autonomous-driving", "video-generation", "world-model" ], "pushed_at": "2025-07-02", "created_at": "2024-05-10", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "OpenDriveLab", "owner_company": "", "owner_location": "Hong Kong", "owner_url": "https://github.com/OpenDriveLab", "owner_repos": 54, "owner_followers": 2675, "owner_bio": "AI for Robotics and Autonomous Driving at The University of Hong Kong (HKU)", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "navigation" ], "score": 4, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "Open-X-Humanoid/TienKung-Lab", "slug": "open-x-humanoid-tienkung-lab", "url": "https://github.com/Open-X-Humanoid/TienKung-Lab", "owner": "Open-X-Humanoid", "name": "TienKung-Lab", "description": "Tien Kung-Lab: Direct IsaacLab Workflow for Legged Robots", "readme": "This framework is an RL-based locomotion control system designed for full-sized humanoid robots, TienKung. It integrates AMP-style rewards with periodic gait rewards, facilitating natural, stable, and efficient walking and running behaviors.", "stars": 870, "stars_scraped": 857, "forks": 119, "watchers": 5, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "embodied-ai", "humanoid-robot", "isaaclab", "isaacsim", "reinforcement-learning", "sim2sim", "tienkung" ], "pushed_at": "2026-07-15", "created_at": "2025-07-03", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Open X-Humanoid", "owner_company": "", "owner_location": "\u4e2d\u56fd", "owner_url": "https://github.com/Open-X-Humanoid", "owner_repos": 24, "owner_followers": 415, "owner_bio": "the first innovation center in China that focuses on the core technology, product development, and application ecosystem construction of humanoid robots.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "alibaba-damo-academy/RynnBrain", "slug": "alibaba-damo-academy-rynnbrain", "url": "https://github.com/alibaba-damo-academy/RynnBrain", "owner": "alibaba-damo-academy", "name": "RynnBrain", "description": "RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Models", "readme": "\ud83d\udcab Project Page | \ud83e\udd17 Hugging Face | \ud83e\udd16 ModelScope | \ud83d\udcda Cookbooks | \ud83d\udcc4 arXiv | \ud83d\udcc4 1.1 paper", "stars": 869, "stars_scraped": 865, "forks": 82, "watchers": 17, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-10", "created_at": "", "archived": false, "paper_ids": [ "2607.17977" ], "owner_type": "Organization", "owner_display": "Alibaba DAMO Academy", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/alibaba-damo-academy", "owner_repos": 82, "owner_followers": 947, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.17977", "slug": "rynnbrain-1-1-towards-more-capable-and-generalizable-embodied-foundati", "title": "RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model", "featured": false } ], "topics": [ "foundation-pretraining" ], "score": 3, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "OpenDCAI/OpenWorldLib", "slug": "opendcai-openworldlib", "url": "https://github.com/OpenDCAI/OpenWorldLib", "owner": "OpenDCAI", "name": "OpenWorldLib", "description": "Unified Codebase for Advanced World Models.", "readme": "Extension repo\uff1a [3D generation] | [VLA] | [simulator]", "stars": 863, "stars_scraped": 860, "forks": 52, "watchers": 13, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "3d-scene-generation", "awesome-world-model", "diffusion-models", "gaussian-splatting", "hunyuan-world", "lingbot-world", "simulator", "vggt", "video-editing", "vla", "vlm", "world-model", "world-models" ], "pushed_at": "2026-08-23", "created_at": "2025-11-21", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "OpenDCAI", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/OpenDCAI", "owner_repos": 42, "owner_followers": 1529, "owner_bio": "Define the future of Data-centric AI together", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "sim2real" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "MarkFzp/humanplus", "slug": "markfzp-humanplus", "url": "https://github.com/MarkFzp/humanplus", "owner": "MarkFzp", "name": "humanplus", "description": "[CoRL 2024] HumanPlus: Humanoid Shadowing and Imitation from Humans", "readme": "Install IsaacGym v4 first from the official source . Place the isaacgym fold inside the HST folder.", "stars": 850, "stars_scraped": 850, "forks": 122, "watchers": 18, "language": "Python", "license": null, "gh_topics": [ "humanoids", "imitation-learning", "reinforcement-learning", "robotics" ], "pushed_at": "2024-07-01", "created_at": "2024-06-12", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Zipeng Fu", "owner_company": "Stanford University", "owner_location": "Palo Alto, CA", "owner_url": "https://github.com/MarkFzp", "owner_repos": 16, "owner_followers": 1146, "owner_bio": "CS PhD at Stanford AI Lab. Working on Robotics and Machine Learning. ", "affiliated_org": "Stanford", "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "MIV-XJTU/FSDrive", "slug": "miv-xjtu-fsdrive", "url": "https://github.com/MIV-XJTU/FSDrive", "owner": "MIV-XJTU", "name": "FSDrive", "description": "[NeurIPS 2025 spotlight] Official implementation for \"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving\"", "readme": "1 Amap, Alibaba Group, 2 Xi\u2019an Jiaotong University, 3 DAMO Academy, Alibaba Group", "stars": 821, "stars_scraped": 821, "forks": 51, "watchers": 25, "language": "Python", "license": null, "gh_topics": [ "autonomous-driving", "cot", "mllm", "vla", "world-model" ], "pushed_at": "2026-05-08", "created_at": "2025-05-27", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "MIV-XJTU", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/MIV-XJTU", "owner_repos": 21, "owner_followers": 62, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "navigation" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "zubair-irshad/Awesome-Robotics-3D", "slug": "zubair-irshad-awesome-robotics-3d", "url": "https://github.com/zubair-irshad/Awesome-Robotics-3D", "owner": "zubair-irshad", "name": "Awesome-Robotics-3D", "description": "A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites", "readme": "Feel free to share this list with others! List curated and maintained by Zubair Irshad . If you have any questions, please get in touch!", "stars": 819, "stars_scraped": 819, "forks": 42, "watchers": 14, "language": null, "license": null, "gh_topics": [ "3d", "benchmarks", "computer-vision", "diffusion-models", "foundation-models", "gaussian-splatting", "grasping", "llm", "manipulation", "navigation", "nerf", "pointclouds", "policy-learning", "pretraining", "robotics", "scene-graph", "simulations", "vision-language-model", "vlm" ], "pushed_at": "2025-12-17", "created_at": "2024-08-12", "archived": false, "paper_ids": [], "owner_type": null, "owner_display": null, "owner_company": "", "owner_location": "", "owner_url": "https://github.com/zubair-irshad", "owner_repos": null, "owner_followers": null, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "dexterous-manipulation", "navigation", "foundation-pretraining" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Robbyant/lingbot-vla-v2", "slug": "robbyant-lingbot-vla-v2", "url": "https://github.com/Robbyant/lingbot-vla-v2", "owner": "Robbyant", "name": "lingbot-vla-v2", "description": "From Foundation to Application", "readme": "Compared with LingBot-VLA 1.0, LingBot-VLA 2.0 improves three core capabilities:", "stars": 800, "stars_scraped": 783, "forks": 66, "watchers": 2, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-10", "created_at": "", "archived": false, "paper_ids": [ "2607.06403" ], "owner_type": "Organization", "owner_display": "Robbyant", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Robbyant", "owner_repos": 10, "owner_followers": 1495, "owner_bio": "Intelligence in Action, Benefits for Everyone", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.06403", "slug": "from-foundation-to-application-improving-vla-models-in-practice", "title": "From Foundation to Application: Improving VLA Models in Practice", "featured": false } ], "topics": [ "vla" ], "score": 3, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "menloresearch/asimov-v0", "slug": "menloresearch-asimov-v0", "url": "https://github.com/menloresearch/asimov-v0", "owner": "menloresearch", "name": "asimov-v0", "description": "v0 of Asimov, an open-source humanoid robot", "readme": "", "stars": 781, "stars_scraped": 778, "forks": 91, "watchers": 26, "language": null, "license": "CERN-OHL-S-2.0", "gh_topics": [ "humanoid", "humanoid-robot", "humanoid-robots", "humanoid-walking", "humanoids", "robotics" ], "pushed_at": "2026-01-28", "created_at": "2026-01-27", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Menlo Research", "owner_company": "", "owner_location": "Singapore", "owner_url": "https://github.com/menloresearch", "owner_repos": 18, "owner_followers": 293, "owner_bio": "Menlo is a Physical AI company that deploys robots to solve real world problems. ", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "2toinf/X-VLA", "slug": "2toinf-x-vla", "url": "https://github.com/2toinf/X-VLA", "owner": "2toinf", "name": "X-VLA", "description": "[ICLR 2026] The offical Implementation of \"Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model\"", "readme": "X-VLA won 1st Place (Champion) at the AgiBot World Challenge , held at IROS 2025 .", "stars": 719, "stars_scraped": 715, "forks": 69, "watchers": 2, "language": "C++", "license": "Apache-2.0", "gh_topics": [ "cloth-folding", "florence-2", "manipulation", "pretrained-models", "robotics", "robotics-dataset", "vision-language-action-model", "vision-language-model" ], "pushed_at": "2026-06-10", "created_at": "2025-09-25", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Jinliang Zheng", "owner_company": "Tsinghua University", "owner_location": "China", "owner_url": "https://github.com/2toinf", "owner_repos": 18, "owner_followers": 99, "owner_bio": "", "affiliated_org": "Tsinghua", "link_sources": [], "papers": [], "topics": [ "vla", "foundation-pretraining" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "leggedrobotics/pace-sim2real", "slug": "leggedrobotics-pace-sim2real", "url": "https://github.com/leggedrobotics/pace-sim2real", "owner": "leggedrobotics", "name": "pace-sim2real", "description": "PACE: A systematic approach for sim-to-real transfer of legged robots, identifying actuator and joint dynamics with standard joint encoders.", "readme": "PACE (Precise Adaptation through Continuous Evolution) bridges the gap between simulation and real hardware by:", "stars": 687, "stars_scraped": 684, "forks": 65, "watchers": 17, "language": "Python", "license": "Apache-2.0", "gh_topics": [], "pushed_at": "2026-08-24", "created_at": "2025-09-05", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Robotic Systems Lab - Legged Robotics at ETH Z\u00fcrich", "owner_company": "", "owner_location": "Z\u00fcrich", "owner_url": "https://github.com/leggedrobotics", "owner_repos": 307, "owner_followers": 3523, "owner_bio": "The Robotic Systems Lab investigates the development of machines and their intelligence to operate in rough and challenging environments. ", "affiliated_org": "ETH Zurich", "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real", "hardware-codesign" ], "score": 9, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "leggedrobotics/robotic_world_model", "slug": "leggedrobotics-robotic-world-model", "url": "https://github.com/leggedrobotics/robotic_world_model", "owner": "leggedrobotics", "name": "robotic_world_model", "description": "Repository for our papers: Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics and Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots", "readme": "and related model-based reinforcement learning methods.", "stars": 670, "stars_scraped": 670, "forks": 54, "watchers": 4, "language": "Python", "license": "Apache-2.0", "gh_topics": [], "pushed_at": "2026-04-08", "created_at": "2025-11-24", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Robotic Systems Lab - Legged Robotics at ETH Z\u00fcrich", "owner_company": "", "owner_location": "Z\u00fcrich", "owner_url": "https://github.com/leggedrobotics", "owner_repos": 307, "owner_followers": 3523, "owner_bio": "The Robotic Systems Lab investigates the development of machines and their intelligence to operate in rough and challenging environments. ", "affiliated_org": "ETH Zurich", "link_sources": [], "papers": [], "topics": [ "world-models", "humanoids", "sim2real", "rl-control" ], "score": 12, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "HorizonRobotics/HoloMotion", "slug": "horizonrobotics-holomotion", "url": "https://github.com/HorizonRobotics/HoloMotion", "owner": "HorizonRobotics", "name": "HoloMotion", "description": "HoloMotion: A Foundation Model for Whole-Body Humanoid Control", "readme": "", "stars": 664, "stars_scraped": 641, "forks": 43, "watchers": 8, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "foundation-models", "humanoid-robot", "motion-tracking", "robotics", "whole-body-control" ], "pushed_at": "2026-08-19", "created_at": "2025-07-30", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Horizon Robotics", "owner_company": "", "owner_location": "Beijing, China", "owner_url": "https://github.com/HorizonRobotics", "owner_repos": 44, "owner_followers": 533, "owner_bio": "To make human life safer and better", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "foundation-pretraining" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "AILab-CVC/SEED", "slug": "ailab-cvc-seed", "url": "https://github.com/AILab-CVC/SEED", "owner": "AILab-CVC", "name": "SEED", "description": "Official implementation of SEED-LLaMA (ICLR 2024).", "readme": "", "stars": 642, "stars_scraped": 642, "forks": 33, "watchers": 16, "language": null, "license": null, "gh_topics": [ "foundation-model", "multimodal", "vision-language" ], "pushed_at": "2024-09-21", "created_at": "", "archived": false, "paper_ids": [ "2310.01218" ], "owner_type": "Organization", "owner_display": "TencentAILab-CVC", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/AILab-CVC", "owner_repos": 18, "owner_followers": 699, "owner_bio": "Tencent AI Lab - Computer Vision Center", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2310.01218", "slug": "making-llama-see-and-draw-with-seed-tokenizer", "title": "Making LLaMA SEE and Draw with SEED Tokenizer", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "ucla-mobility/AutoVLA", "slug": "ucla-mobility-autovla", "url": "https://github.com/ucla-mobility/AutoVLA", "owner": "ucla-mobility", "name": "AutoVLA", "description": "[NeurIPS 2025] AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning", "readme": "AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning", "stars": 632, "stars_scraped": 630, "forks": 51, "watchers": 37, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "autonomous-driving", "grpo", "reinforcement-finetuning", "vision-language-action" ], "pushed_at": "2026-05-29", "created_at": "2025-06-14", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "UCLA Mobility Lab", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/ucla-mobility", "owner_repos": 32, "owner_followers": 218, "owner_bio": "A research lab dedicated to harnessing system theories and tools, such as AI, control, robotics, and optimization for smart vehicles and transportation", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "navigation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "LeCAR-Lab/ABS", "slug": "lecar-lab-abs", "url": "https://github.com/LeCAR-Lab/ABS", "owner": "LeCAR-Lab", "name": "ABS", "description": "[RSS 2024] Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion", "readme": "Tairan He* , Chong Zhang* , Wenli Xiao , Guanqi He , Changliu Liu , Guanya Shi", "stars": 624, "stars_scraped": 623, "forks": 49, "watchers": 15, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2024-07-11", "created_at": "2024-01-29", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "LeCAR Lab at CMU", "owner_company": "", "owner_location": "United States of America", "owner_url": "https://github.com/LeCAR-Lab", "owner_repos": 28, "owner_followers": 872, "owner_bio": "Learning and Control for Agile Robotics Lab at CMU", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "notmahi/dobb-e", "slug": "notmahi-dobb-e", "url": "https://github.com/notmahi/dobb-e", "owner": "notmahi", "name": "dobb-e", "description": "Dobb\u00b7E: An open-source, general framework for learning household robotic manipulation", "readme": "Project webpage \u00b7 Documentation (gitbooks) \u00b7 Paper", "stars": 621, "stars_scraped": 621, "forks": 57, "watchers": 13, "language": "G-code", "license": "MIT", "gh_topics": [ "behavior-cloning", "imitation-learning", "robot-learning", "robotics" ], "pushed_at": "2024-10-15", "created_at": "2023-11-27", "archived": false, "paper_ids": [ "2311.16098" ], "owner_type": "User", "owner_display": "Nur Muhammad \"Mahi\" Shafiullah", "owner_company": "New York University", "owner_location": "New York, NY", "owner_url": "https://github.com/notmahi", "owner_repos": 28, "owner_followers": 163, "owner_bio": "Building generally intelligent robots that just work everywhere, out of the box.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2311.16098", "slug": "on-bringing-robots-home", "title": "On Bringing Robots Home", "featured": false } ], "topics": [], "score": 2, "from_paper": true, "link_strength": "endorsed", "stale": true }, { "full_name": "dexmal/realtime-vla", "slug": "dexmal-realtime-vla", "url": "https://github.com/dexmal/realtime-vla", "owner": "dexmal", "name": "realtime-vla", "description": "Running VLA at 30Hz frame rate and 480Hz trajectory frequency", "readme": "Pi0 (Triton) latency on RTX 4090 (max boosted clock 2.79GHz) for one set of observations (10 flow steps, chunk size 63, empty prompt) is as follows:", "stars": 607, "stars_scraped": 608, "forks": 45, "watchers": 7, "language": null, "license": null, "gh_topics": [ "4090", "pi0", "real-time", "vla" ], "pushed_at": "2026-02-10", "created_at": "", "archived": false, "paper_ids": [ "2510.26742" ], "owner_type": "Organization", "owner_display": "Dexmal", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/dexmal", "owner_repos": 8, "owner_followers": 105, "owner_bio": "Build Intelligent, Useful and Trustworthy Robots to Make Our Life Better.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2510.26742", "slug": "running-vlas-at-real-time-speed", "title": "Running VLAs at Real-time Speed", "featured": false } ], "topics": [ "vla" ], "score": 3, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "MishaLaskin/curl", "slug": "mishalaskin-curl", "url": "https://github.com/MishaLaskin/curl", "owner": "MishaLaskin", "name": "curl", "description": "CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning", "readme": "To train a CURL agent on the cartpole swingup task from image-based observations run bash script/run.sh from the root of this directory. The run.sh file contains the following command, which you can modify to try different environments / hyperparamters.", "stars": 605, "stars_scraped": 605, "forks": 92, "watchers": 10, "language": null, "license": null, "gh_topics": [ "contrastive-learning", "contrastive-loss", "contrastive-predictive-coding", "curl", "deep-learning", "deep-learning-algorithms", "deep-neural-networks", "deep-q-learning", "deep-q-network", "deep-reinforcement-learning", "deep-rl", "deeplearning", "deeplearning-ai", "gpu", "model-free-rl", "off-policy", "reinforcement-agents", "reinforcement-learning", "reinforcement-learning-algorithms", "sac" ], "pushed_at": "2020-10-28", "created_at": "", "archived": false, "paper_ids": [ "2004.04136" ], "owner_type": "User", "owner_display": "Michael Laskin", "owner_company": "DeepMind", "owner_location": "New York City", "owner_url": "https://github.com/MishaLaskin", "owner_repos": 52, "owner_followers": 270, "owner_bio": "Senior Research Scientist at DeepMind", "affiliated_org": "Google DeepMind", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2004.04136", "slug": "curl-contrastive-unsupervised-representations-for-reinforcement-learni", "title": "CURL: Contrastive Unsupervised Representations for Reinforcement Learning", "featured": false } ], "topics": [ "rl-control" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "sail-sg/MDT", "slug": "sail-sg-mdt", "url": "https://github.com/sail-sg/MDT", "owner": "sail-sg", "name": "MDT", "description": "Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)", "readme": "MDTv2 achieves superior image synthesis performance, e.g., a new SOTA FID score of 1.58 on the ImageNet dataset, and has more than 10\u00d7 faster learning speed than the previous SOTA DiT.", "stars": 596, "stars_scraped": 596, "forks": 42, "watchers": 15, "language": null, "license": null, "gh_topics": [], "pushed_at": "2024-04-23", "created_at": "", "archived": false, "paper_ids": [ "2303.14389" ], "owner_type": "Organization", "owner_display": "Sea AI Lab", "owner_company": "", "owner_location": "Singapore", "owner_url": "https://github.com/sail-sg", "owner_repos": 101, "owner_followers": 781, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2303.14389", "slug": "mdtv2-masked-diffusion-transformer-is-a-strong-image-synthesizer", "title": "MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "xiaomi-research/recogdrive", "slug": "xiaomi-research-recogdrive", "url": "https://github.com/xiaomi-research/recogdrive", "owner": "xiaomi-research", "name": "recogdrive", "description": "[ICLR 2026] ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving", "readme": "(*) Equal contribution. (\u2020) Project leader. (\u2709) Corresponding author.", "stars": 594, "stars_scraped": 590, "forks": 73, "watchers": 12, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "autonomous-driving", "diffusion-policy", "end-to-end-a", "navsim", "reinforcement-learning", "vision-language-action", "vision-language-models" ], "pushed_at": "2026-08-18", "created_at": "2025-06-05", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Xiaomi Research", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/xiaomi-research", "owner_repos": 50, "owner_followers": 421, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "navigation" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "RobotecAI/rai", "slug": "robotecai-rai", "url": "https://github.com/RobotecAI/rai", "owner": "RobotecAI", "name": "rai", "description": "RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.", "readme": "", "stars": 575, "stars_scraped": 573, "forks": 74, "watchers": 9, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "ai", "ai-agents-framework", "embodied-agent", "embodied-agents", "embodied-ai", "embodied-artificial-intelligence", "generative-ai", "llm", "multi-agent-systems", "multimodal", "o3de", "physical-ai", "robotec", "robotics", "ros2", "vlm" ], "pushed_at": "2026-08-12", "created_at": "2024-06-04", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Robotec.ai", "owner_company": "", "owner_location": "Poland", "owner_url": "https://github.com/RobotecAI", "owner_repos": 88, "owner_followers": 280, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "sii-research/tau-0-vla", "slug": "sii-research-tau-0-vla", "url": "https://github.com/sii-research/tau-0-vla", "owner": "sii-research", "name": "tau-0-vla", "description": "This repo is the official implementation of \"\u03c40-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation\".", "readme": "This repo is the official implementation of \u03c4\u2080-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation .", "stars": 563, "stars_scraped": 525, "forks": 16, "watchers": 2, "language": "Python", "license": "Apache-2.0", "gh_topics": [], "pushed_at": "2026-08-26", "created_at": "2026-07-26", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Shanghai Innovation Institute", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/sii-research", "owner_repos": 26, "owner_followers": 383, "owner_bio": "SII is an institution dedicated to innovation in education and research", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "foundation-pretraining" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "legubiao/quadruped_ros2_control", "slug": "legubiao-quadruped-ros2-control", "url": "https://github.com/legubiao/quadruped_ros2_control", "owner": "legubiao", "name": "quadruped_ros2_control", "description": "ROS2-Control implementations for Quadruped robots, include sim2real", "readme": "Todo List:", "stars": 562, "stars_scraped": 561, "forks": 71, "watchers": 5, "language": "C++", "license": "Apache-2.0", "gh_topics": [ "deep-robotics", "gazebo", "legged-robots", "mujoco", "ocs2", "rl", "ros2-control", "unitree", "xiaomi" ], "pushed_at": "2026-02-22", "created_at": "2024-09-09", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "HUANG ZHENBIAO", "owner_company": "National University of Singapore", "owner_location": "Singapore", "owner_url": "https://github.com/legubiao", "owner_repos": 30, "owner_followers": 179, "owner_bio": "NUS Msc Robotics student", "affiliated_org": "NUS", "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real" ], "score": 8, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "OpenDriveLab/WholebodyVLA", "slug": "opendrivelab-wholebodyvla", "url": "https://github.com/OpenDriveLab/WholebodyVLA", "owner": "OpenDriveLab", "name": "WholebodyVLA", "description": "[ICLR 2026] Towards Unified Latent VLA for Whole-body Loco-manipulation Control", "readme": "", "stars": 553, "stars_scraped": 550, "forks": 18, "watchers": 11, "language": null, "license": "MIT", "gh_topics": [ "humanoid-robot", "loco-manipulation", "vision-language-action" ], "pushed_at": "2026-05-25", "created_at": "2025-12-10", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "OpenDriveLab", "owner_company": "", "owner_location": "Hong Kong", "owner_url": "https://github.com/OpenDriveLab", "owner_repos": 54, "owner_followers": 2675, "owner_bio": "AI for Robotics and Autonomous Driving at The University of Hong Kong (HKU)", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "humanoids" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "RoboVerseOrg/Simulately", "slug": "roboverseorg-simulately", "url": "https://github.com/RoboVerseOrg/Simulately", "owner": "RoboVerseOrg", "name": "Simulately", "description": "A universal summary of current robotics simulators", "readme": "The website is built with Docusaurus, powered by Cloudflare Pages.", "stars": 551, "stars_scraped": 550, "forks": 30, "watchers": 20, "language": "TypeScript", "license": "Apache-2.0", "gh_topics": [ "awesome", "embodied-ai", "robotics", "robotics-programming", "simulation", "simulator" ], "pushed_at": "2025-07-22", "created_at": "2023-10-12", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "RoboVerse", "owner_company": "", "owner_location": "United States of America", "owner_url": "https://github.com/RoboVerseOrg", "owner_repos": 7, "owner_followers": 69, "owner_bio": "RoboVerse Platform", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "sou350121/VLA-Handbook", "slug": "sou350121-vla-handbook", "url": "https://github.com/sou350121/VLA-Handbook", "owner": "sou350121", "name": "VLA-Handbook", "description": "\u672c\u9879\u76ee\u65e8\u5728\u4e3a\u81f4\u529b\u4e8e\u8fdb\u5165VLA(Vision-Language-Action)\u9886\u57df\u7684\u7b97\u6cd5\u5de5\u7a0b\u5e08\u63d0\u4f9b\u4e00\u4efd\u5168\u4e2d\u6587\u3001\u5b9e\u6218\u5bfc\u5411\u7684\u5b66\u4e60/\u9762\u8bd5\u624b\u518c\u3002 \u4e0d\u540c\u4e8e\u901a\u7528\u7684 CV/NLP \u9762\u8bd5\u6307\u5357\uff0c\u672c\u9879\u76ee\u805a\u7126\u4e8e Robotics \u7279\u6709\u7684\u6311\u6218", "readme": "\ud83d\udcca PULSAR \u7167\u89c1 \u00b7 \u6bcf\u65e5\u5317\u4eac\u65f6\u95f4 12:00 \u66f4\u65b0\uff0c\u51cf\u5c11\u4fe1\u606f\u7126\u8651 \u2014 sou350121.github.io/pulsar-web", "stars": 551, "stars_scraped": 533, "forks": 36, "watchers": 6, "language": "HTML", "license": "CC-BY-4.0", "gh_topics": [ "chinese", "deep-learning", "embodied-ai", "llm", "robot-learning", "robotics", "vision-language-action", "vla" ], "pushed_at": "2026-08-26", "created_at": "2025-11-23", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "KenSou", "owner_company": "", "owner_location": "Macau", "owner_url": "https://github.com/sou350121", "owner_repos": 61, "owner_followers": 26, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "isaac-sim/IsaacLab-Arena", "slug": "isaac-sim-isaaclab-arena", "url": "https://github.com/isaac-sim/IsaacLab-Arena", "owner": "isaac-sim", "name": "IsaacLab-Arena", "description": "Isaac Lab - Arena is a robotics simulation framework that enhances NVIDIA Isaac Lab by providing a composable, scalable system for creating diverse simulation environments and evaluating robot learning policies. The framework enables developers to rapidly prototype and test robotic tasks with various robot embodiments, objects, and environments.", "readme": "Warning", "stars": 546, "stars_scraped": 539, "forks": 93, "watchers": 4, "language": "Python", "license": "NOASSERTION", "gh_topics": [], "pushed_at": "2026-08-26", "created_at": "2025-08-15", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "NVIDIA Isaac Sim", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/isaac-sim", "owner_repos": 21, "owner_followers": 1720, "owner_bio": "", "affiliated_org": "NVIDIA", "link_sources": [], "papers": [], "topics": [], "score": 8, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "InternRobotics/InternVLA-A-series", "slug": "internrobotics-internvla-a-series", "url": "https://github.com/InternRobotics/InternVLA-A-series", "owner": "InternRobotics", "name": "InternVLA-A-series", "description": "InternVLA-A1: Unifying Understanding, Generation, and Action for Robotic Manipulation\u200b", "readme": "Note", "stars": 539, "stars_scraped": 539, "forks": 43, "watchers": 3, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "manipulation", "robotics", "vision-language-action-model" ], "pushed_at": "2026-07-20", "created_at": "2025-09-18", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Intern Robotics", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/InternRobotics", "owner_repos": 88, "owner_followers": 1805, "owner_bio": "Building inclusive infrastructure for Embodied AI, from Shanghai AI Lab.", "affiliated_org": "Shanghai AI Lab", "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "GigaAI-research/General-World-Models-Survey", "slug": "gigaai-research-general-world-models-survey", "url": "https://github.com/GigaAI-research/General-World-Models-Survey", "owner": "GigaAI-research", "name": "General-World-Models-Survey", "description": "", "readme": "", "stars": 525, "stars_scraped": 525, "forks": 28, "watchers": 16, "language": null, "license": null, "gh_topics": [], "pushed_at": "2025-10-30", "created_at": "", "archived": false, "paper_ids": [ "2405.03520" ], "owner_type": "User", "owner_display": "GigaAI-research", "owner_company": "GigaAI", "owner_location": "Beijing", "owner_url": "https://github.com/GigaAI-research", "owner_repos": 25, "owner_followers": 177, "owner_bio": "GigaAI Research", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2405.03520", "slug": "is-sora-a-world-simulator-a-comprehensive-survey-on-general-world-mode", "title": "Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond", "featured": false } ], "topics": [ "world-models" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "Visionary-Laboratory/visionary", "slug": "visionary-laboratory-visionary", "url": "https://github.com/Visionary-Laboratory/visionary", "owner": "Visionary-Laboratory", "name": "visionary", "description": "Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform", "readme": "Shanghai AI Laboratory \u00b7 Sichuan University \u00b7 The University of Tokyo \u00b7 Shanghai Jiao Tong University \u00b7 Northwestern Polytechnical University", "stars": 523, "stars_scraped": 522, "forks": 34, "watchers": 7, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "3dgs", "4dgs", "avatar", "computer-graphics", "computer-vision", "diffusion-models", "frontend", "gaussian-splatting", "javascript", "neural-rendering", "onnx", "siggraph", "siggraph-asia", "threejs", "typescript", "viewer", "webdev", "webgpu", "world-model" ], "pushed_at": "2026-06-26", "created_at": "2025-12-07", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Visionary-Laboratory", "owner_company": "", "owner_location": "China", "owner_url": "https://github.com/Visionary-Laboratory", "owner_repos": 7, "owner_followers": 39, "owner_bio": "Visionary Laboratory (\u7a7a\u95f4\u591a\u5a92\u4f53\u5b9e\u9a8c\u5ba4) at Shanghai Jiao Tong University, led by Prof. Zhihang Zhong.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "spatial-3d" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "TX-Leo/HumanEgo", "slug": "tx-leo-humanego", "url": "https://github.com/TX-Leo/HumanEgo", "owner": "TX-Leo", "name": "HumanEgo", "description": "HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos", "readme": "", "stars": 509, "stars_scraped": 504, "forks": 49, "watchers": 2, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-25", "created_at": "", "archived": false, "paper_ids": [ "2605.24934" ], "owner_type": "User", "owner_display": "Zhi (Leo) Wang", "owner_company": "Amazon FAR", "owner_location": "San Francisco", "owner_url": "https://github.com/TX-Leo", "owner_repos": 84, "owner_followers": 145, "owner_bio": "Research Intern@Amazon FAR, Robotics PhD @ UMD\ud83e\udd16\ufe0f;Doing robot learning from human data!\r\nPrev: Tsinghua EE, Microsoft Research, UIUC CS", "affiliated_org": "Amazon", "link_sources": [ "paper-fulltext" ], "papers": [ { "id": "2605.24934", "slug": "humanego-zero-shot-robot-learning-from-minutes-of-human-egocentric-vid", "title": "HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos", "featured": true } ], "topics": [ "egocentric-data" ], "score": 3, "from_paper": true, "link_strength": "named-after-paper", "stale": false }, { "full_name": "KlingAIResearch/VideoAlign", "slug": "klingairesearch-videoalign", "url": "https://github.com/KlingAIResearch/VideoAlign", "owner": "KlingAIResearch", "name": "VideoAlign", "description": "[NeurIPS 2025] Improving Video Generation with Human Feedback", "readme": "This versatile reward model can be used for data filtering, guidance, reject sampling, DPO, and other RL methods.", "stars": 501, "stars_scraped": 501, "forks": 13, "watchers": 9, "language": null, "license": null, "gh_topics": [], "pushed_at": "2025-09-24", "created_at": "", "archived": false, "paper_ids": [ "2501.13918" ], "owner_type": "Organization", "owner_display": "KlingAI Research", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/KlingAIResearch", "owner_repos": 55, "owner_followers": 1207, "owner_bio": "The Kling Team is building next-generation multimodal world models across video, audio, text, 3D, and beyond. Welcome to join us!", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2501.13918", "slug": "improving-video-generation-with-human-feedback", "title": "Improving Video Generation with Human Feedback", "featured": false } ], "topics": [ "rl-control", "video-generation" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "chengxuxin/expressive-humanoid", "slug": "chengxuxin-expressive-humanoid", "url": "https://github.com/chengxuxin/expressive-humanoid", "owner": "chengxuxin", "name": "expressive-humanoid", "description": "[RSS 2024]: Expressive Whole-Body Control for Humanoid Robots", "readme": "", "stars": 498, "stars_scraped": 498, "forks": 40, "watchers": 4, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "human-motion", "imitation-learning", "reinforcement-learning", "sim-to-real" ], "pushed_at": "2025-03-30", "created_at": "2024-07-14", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Xuxin Cheng", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/chengxuxin", "owner_repos": 22, "owner_followers": 387, "owner_bio": "\r\nUC Berkeley \ud83d\udc49 CMU \ud83d\udc49 UC San Diego\r\n", "affiliated_org": "UC Berkeley", "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real" ], "score": 6, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "shannon112/awesome-ros-mobile-robot", "slug": "shannon112-awesome-ros-mobile-robot", "url": "https://github.com/shannon112/awesome-ros-mobile-robot", "owner": "shannon112", "name": "awesome-ros-mobile-robot", "description": " \ud83d\ude0e A curated list of awesome mobile robots study resources based on ROS (including SLAM, odometry and navigation, manipulation)", "readme": "", "stars": 497, "stars_scraped": 497, "forks": 103, "watchers": 10, "language": null, "license": null, "gh_topics": [ "awesome-list", "manipulation", "mobile-robots", "navigation", "odometry", "robotics", "ros", "slam" ], "pushed_at": "2025-10-31", "created_at": "2019-02-09", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "shannon112", "owner_company": "", "owner_location": "Taiwan", "owner_url": "https://github.com/shannon112", "owner_repos": 86, "owner_followers": 80, "owner_bio": "Robotics Hacker for Fun and Coolness \ud83d\ude0e\ud83e\udd16\ud83d\udee5", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "spatial-3d", "navigation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "mll-lab-nu/VAGEN", "slug": "mll-lab-nu-vagen", "url": "https://github.com/mll-lab-nu/VAGEN", "owner": "mll-lab-nu", "name": "VAGEN", "description": "World model reinforcement learning for multi-turn VLM agents. RL for vision framework (NeurIPS 2025).", "readme": "", "stars": 493, "stars_scraped": 493, "forks": 60, "watchers": 7, "language": "Python", "license": "MIT", "gh_topics": [ "agent", "embodied-ai", "multi-turn-reinforcement-learning", "neurips-2025", "reinforcement-learning", "rl-for-vision", "vision-language-model", "vision-language-models", "vlm-agent", "vlm-agents", "world-model", "world-models" ], "pushed_at": "2026-08-26", "created_at": "2025-03-04", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "MLL Lab", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/mll-lab-nu", "owner_repos": 14, "owner_followers": 57, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "rl-control" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "gaiyi7788/awesome-legged-locomotion-learning", "slug": "gaiyi7788-awesome-legged-locomotion-learning", "url": "https://github.com/gaiyi7788/awesome-legged-locomotion-learning", "owner": "gaiyi7788", "name": "awesome-legged-locomotion-learning", "description": "A curated list of resources relevant to legged locomotion learning of robotics.", "readme": "[ legged_gym ]: Isaac Gym Environments for Legged Robots", "stars": 485, "stars_scraped": 484, "forks": 45, "watchers": 15, "language": null, "license": null, "gh_topics": [ "awesome", "locomotion", "reinforcement-learning", "robotics" ], "pushed_at": "2023-07-10", "created_at": "2023-01-17", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Pengyu Chen", "owner_company": "Computer Science and Technology\uff0cNorthwestern Polytechnical University", "owner_location": "Xi'an", "owner_url": "https://github.com/gaiyi7788", "owner_repos": 209, "owner_followers": 30, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 7, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "MarSaKi/ETPNav", "slug": "marsaki-etpnav", "url": "https://github.com/MarSaKi/ETPNav", "owner": "MarSaKi", "name": "ETPNav", "description": "[TPAMI 2024] Official repo of \"ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments\"", "readme": "Leadboard:", "stars": 484, "stars_scraped": 484, "forks": 39, "watchers": 1, "language": "Python", "license": "MIT", "gh_topics": [ "embodied-ai", "topological-maps", "vision-and-language", "vision-language-navigation", "vision-language-pre-training" ], "pushed_at": "2026-04-27", "created_at": "2023-04-06", "archived": false, "paper_ids": [ "2304.03047" ], "owner_type": "User", "owner_display": "Dong An", "owner_company": "MBZUAI", "owner_location": "Abu Dhabi, UAE", "owner_url": "https://github.com/MarSaKi", "owner_repos": 52, "owner_followers": 95, "owner_bio": "Research Scientist at MBZUAI IFM", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2304.03047", "slug": "etpnav-evolving-topological-planning-for-vision-language-navigation-in", "title": "ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments", "featured": false } ], "topics": [ "navigation", "foundation-pretraining" ], "score": 2, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "JeffreyYH/Awesome-Generalist-Robots-via-Foundation-Models", "slug": "jeffreyyh-awesome-generalist-robots-via-foundation-models", "url": "https://github.com/JeffreyYH/Awesome-Generalist-Robots-via-Foundation-Models", "owner": "JeffreyYH", "name": "Awesome-Generalist-Robots-via-Foundation-Models", "description": "Paper list in the survey paper: Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis", "readme": "Foundation models used in Robotics . For these papers, the authors apply existing vision and language foundation models, such as LLM, VLM, vision FM and image and video generation models in modules of robotics, such as perception, action generation, task planning. We also include perspectives such as action grounding, traing data generation, and world modeling in this category.", "stars": 468, "stars_scraped": 468, "forks": 28, "watchers": 12, "language": null, "license": null, "gh_topics": [ "foundation-models", "foundation-models-for-robotics", "general-purpose-robots", "generalist-robots", "vision-language-action-model", "world-action-model", "world-model" ], "pushed_at": "2026-06-25", "created_at": "2023-06-20", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Yafei Hu", "owner_company": "Carnegie Mellon University", "owner_location": "Boston, MA", "owner_url": "https://github.com/JeffreyYH", "owner_repos": 7, "owner_followers": 41, "owner_bio": "Robotic researcher interested in 3D Vision for Robotics. CMU PhD. ", "affiliated_org": "CMU", "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "foundation-pretraining", "video-generation" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "worldbench/awesome-vla-for-ad", "slug": "worldbench-awesome-vla-for-ad", "url": "https://github.com/worldbench/awesome-vla-for-ad", "owner": "worldbench", "name": "awesome-vla-for-ad", "description": "\ud83c\udf10 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future", "readme": "This survey reviews vision-action (VA) models and vision-language-action (VLA) models for autonomous driving. We trace the evolution from early VA approaches to modern VLA frameworks, and organize existing methods into two principal paradigms:", "stars": 465, "stars_scraped": 465, "forks": 40, "watchers": 15, "language": "HTML", "license": "MIT", "gh_topics": [ "3d", "autonomous-driving", "awesome-list", "embodied-ai", "large-language-models", "llm", "multi-modal", "multimodal-large-language-models", "self-driving", "vision-language", "vision-language-action", "vision-language-models", "vla", "vlm" ], "pushed_at": "2026-08-21", "created_at": "2025-09-07", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "worldbench", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/worldbench", "owner_repos": 29, "owner_followers": 148, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "navigation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "ugurkanates/awesome-real-world-rl", "slug": "ugurkanates-awesome-real-world-rl", "url": "https://github.com/ugurkanates/awesome-real-world-rl", "owner": "ugurkanates", "name": "awesome-real-world-rl", "description": "Great resources for making Reinforcement Learning work in Real Life situations. Papers,projects and more. ", "readme": "This list is big compilation of all things trying to adapt Reinforcement Learning techniques in real world.Either it's mixing real world data into mix or trying to adapt simulations in a better way.It will also include some of Imitation Learning and Meta Learning along the way. If you have anything missing feel free to open a PR,I'm all for community contributions.", "stars": 458, "stars_scraped": 458, "forks": 51, "watchers": 20, "language": null, "license": "CC0-1.0", "gh_topics": [ "awesome", "awesome-list", "gans", "imitation-learning", "meta-learning", "reinforcement-learning", "robotics", "sim2real", "simulation" ], "pushed_at": "2022-10-28", "created_at": "2020-06-29", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Ugurkan Ates", "owner_company": "Microsoft", "owner_location": "Prague,Czechia - Istanbul, Turkey", "owner_url": "https://github.com/ugurkanates", "owner_repos": 61, "owner_followers": 192, "owner_bio": "Developer - Daydreamer. \r\n Focused on Deep Reinforcement Learning.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real", "imitation-diffusion", "rl-control" ], "score": 6, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "yang-zj1026/legged-loco", "slug": "yang-zj1026-legged-loco", "url": "https://github.com/yang-zj1026/legged-loco", "owner": "yang-zj1026", "name": "legged-loco", "description": "Low-level locomotion policy training in Isaac Lab", "readme": "Create a new conda environment with python 3.10.", "stars": 452, "stars_scraped": 451, "forks": 40, "watchers": 1, "language": "Python", "license": "MIT", "gh_topics": [], "pushed_at": "2025-03-07", "created_at": "2024-12-13", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Zhaojing Yang", "owner_company": "UCSD", "owner_location": "", "owner_url": "https://github.com/yang-zj1026", "owner_repos": 16, "owner_followers": 73, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 7, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "microsoft/CogACT", "slug": "microsoft-cogact", "url": "https://github.com/microsoft/CogACT", "owner": "microsoft", "name": "CogACT", "description": "A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation", "readme": "We recommend using Miniconda and setting up an environment:", "stars": 431, "stars_scraped": 431, "forks": 40, "watchers": 7, "language": "Python", "license": "MIT", "gh_topics": [ "embodied-ai" ], "pushed_at": "2025-10-30", "created_at": "2024-11-26", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Microsoft", "owner_company": "", "owner_location": "Redmond, WA", "owner_url": "https://github.com/microsoft", "owner_repos": 8285, "owner_followers": 128217, "owner_bio": "Open source projects and samples from Microsoft", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "softmata/horus", "slug": "softmata-horus", "url": "https://github.com/softmata/horus", "owner": "softmata", "name": "horus", "description": "Fastest Robotics Runtime System. If phones have Android, robots deserve HORUS.", "readme": "", "stars": 425, "stars_scraped": 422, "forks": 31, "watchers": 9, "language": "Rust", "license": "Apache-2.0", "gh_topics": [ "artificial-intelligence", "automation", "autonomous-vehicles", "distributed-systems", "drivers", "drones", "framework", "humanoid", "humanoid-robot", "middleware", "python", "real-time", "robotframework", "robotics", "robotics-programming", "robots", "ros", "ros2", "rust" ], "pushed_at": "2026-08-24", "created_at": "2025-10-17", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "HORUS", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/softmata", "owner_repos": 8, "owner_followers": 27, "owner_bio": "We develop accessible and performant infrastructure for you to build robots", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "navigation" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "RealXiaoze/humanoid-motion-intelligence", "slug": "realxiaoze-humanoid-motion-intelligence", "url": "https://github.com/RealXiaoze/humanoid-motion-intelligence", "owner": "RealXiaoze", "name": "humanoid-motion-intelligence", "description": "\u4eba\u5f62\u673a\u5668\u4eba\u8fd0\u52a8\u667a\u80fd\u8bba\u6587\u3001\u5f00\u6e90\u9879\u76ee\u3001\u4ea7\u4e1a\u4e0e\u6c42\u804c\u77e5\u8bc6\u5e93", "readme": "\u8fd9\u4e2a\u77e5\u8bc6\u5e93\u56f4\u7ed5\u4eba\u5f62\u673a\u5668\u4eba\u8fd0\u52a8\u667a\u80fd\u7684\u5b8c\u6574\u7814\u53d1\u94fe\u7ec4\u7ec7\u5185\u5bb9\uff0c\u5e2e\u52a9\u8bfb\u8005\u628a\u5355\u7bc7\u8bba\u6587\u3001\u5f00\u6e90\u9879\u76ee\u3001\u516c\u53f8\u52a8\u6001\u548c\u5c97\u4f4d\u8981\u6c42\u653e\u56de\u540c\u4e00\u5f20\u95ee\u9898\u5730\u56fe\u4e2d\u3002", "stars": 423, "stars_scraped": 397, "forks": 30, "watchers": 1, "language": null, "license": "NOASSERTION", "gh_topics": [ "embodied-ai", "humanoid-robotics", "locomotion", "motion-control", "reinforcement-learning", "robot-learning", "sim2real", "vla" ], "pushed_at": "2026-08-26", "created_at": "2026-07-19", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "XiaoZe", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/RealXiaoze", "owner_repos": 1, "owner_followers": 18, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "humanoids", "sim2real" ], "score": 9, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "MishaLaskin/rad", "slug": "mishalaskin-rad", "url": "https://github.com/MishaLaskin/rad", "owner": "MishaLaskin", "name": "rad", "description": "RAD: Reinforcement Learning with Augmented Data ", "readme": "All of the dependencies are in the conda_env.yml file. They can be installed manually or with the following command:", "stars": 416, "stars_scraped": 416, "forks": 74, "watchers": 13, "language": null, "license": null, "gh_topics": [ "codebase", "data-", "data-augmentations", "deep-learning", "deep-learning-algorithms", "deep-neural-networks", "deep-q-learning", "deep-q-network", "deep-reinforcement-learning", "deeplearning-ai", "dm-control", "model-free", "mujoc", "off-policy", "ppo", "rad", "reinforcement-learning", "rl", "sac", "soft-actor-critic" ], "pushed_at": "2021-03-29", "created_at": "", "archived": false, "paper_ids": [ "2004.14990" ], "owner_type": "User", "owner_display": "Michael Laskin", "owner_company": "DeepMind", "owner_location": "New York City", "owner_url": "https://github.com/MishaLaskin", "owner_repos": 52, "owner_followers": 270, "owner_bio": "Senior Research Scientist at DeepMind", "affiliated_org": "Google DeepMind", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2004.14990", "slug": "reinforcement-learning-with-augmented-data", "title": "Reinforcement Learning with Augmented Data", "featured": false } ], "topics": [ "rl-control" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "dexmal/opendm", "slug": "dexmal-opendm", "url": "https://github.com/dexmal/opendm", "owner": "dexmal", "name": "opendm", "description": "An Open-World Foundation Model for General-Purpose Embodied Intelligence.", "readme": "English | \u7b80\u4f53\u4e2d\u6587", "stars": 412, "stars_scraped": 314, "forks": 26, "watchers": 2, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "embodied-ai", "embodied-intelligence", "robotics", "vision-language-action", "vla" ], "pushed_at": "2026-08-26", "created_at": "2026-07-06", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Dexmal", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/dexmal", "owner_repos": 8, "owner_followers": 105, "owner_bio": "Build Intelligent, Useful and Trustworthy Robots to Make Our Life Better.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "foundation-pretraining" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "rhett-chen/Robotic-grasping-papers", "slug": "rhett-chen-robotic-grasping-papers", "url": "https://github.com/rhett-chen/Robotic-grasping-papers", "owner": "rhett-chen", "name": "Robotic-grasping-papers", "description": "paper list of robotic grasping and some related works", "readme": "[T-RO2023] Deep Learning Approaches to Grasp Synthesis: A Review, [ Project ], [ Paper ].", "stars": 407, "stars_scraped": 407, "forks": 29, "watchers": 8, "language": null, "license": null, "gh_topics": [ "6d-pose", "general-grasp", "grasp", "grasping", "manipulation", "paper-list", "papers", "robotic-grasping", "robotic-manipulation", "robotics", "semantic-grasp", "task-oriented-grasp", "visual-grounding" ], "pushed_at": "2024-10-31", "created_at": "2022-03-29", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Zibo Chen", "owner_company": "Sun Yat-sen University", "owner_location": "Guangzhou", "owner_url": "https://github.com/rhett-chen", "owner_repos": 14, "owner_followers": 50, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "dexterous-manipulation" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "keon/awesome-physical-ai", "slug": "keon-awesome-physical-ai", "url": "https://github.com/keon/awesome-physical-ai", "owner": "keon", "name": "awesome-physical-ai", "description": "A curated list of academic papers and resources on Physical AI \u2014 focusing on Vision-Language-Action (VLA) models, world models, embodied ai, and robotic foundation models.", "readme": "Core vision-language models that serve as pretrained backbones for Physical AI systems.", "stars": 401, "stars_scraped": 395, "forks": 42, "watchers": 5, "language": null, "license": "CC0-1.0", "gh_topics": [ "awesome", "embodied-ai", "foundational-models", "physical-ai", "robotics", "visual-language-action-models", "vla" ], "pushed_at": "2026-06-24", "created_at": "2026-01-12", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Keon", "owner_company": "Om Labs", "owner_location": "New York City", "owner_url": "https://github.com/keon", "owner_repos": 164, "owner_followers": 3083, "owner_bio": "Co-founder @ Om Labs,\r\nex-Uber", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "foundation-pretraining", "video-generation" ], "score": 11, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "isri-aist/RoboManipBaselines", "slug": "isri-aist-robomanipbaselines", "url": "https://github.com/isri-aist/RoboManipBaselines", "owner": "isri-aist", "name": "RoboManipBaselines", "description": "A software framework integrating various imitation learning methods and benchmark environments for robotic manipulation", "readme": "A software framework integrating various imitation learning methods and benchmark environments for robotic manipulation. Provides easy-to-use baselines for policy training, evaluation, and deployment.", "stars": 395, "stars_scraped": 395, "forks": 56, "watchers": 14, "language": "Python", "license": "BSD-2-Clause", "gh_topics": [ "imitation-learning", "robot-learning", "robot-manipulation" ], "pushed_at": "2026-06-29", "created_at": "2024-03-23", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Intelligent Systems Research Institute, AIST", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/isri-aist", "owner_repos": 133, "owner_followers": 175, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "imitation-diffusion" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "keivalya/mini-vla", "slug": "keivalya-mini-vla", "url": "https://github.com/keivalya/mini-vla", "owner": "keivalya", "name": "mini-vla", "description": "a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to generate actions", "readme": "it is far from being production-ready! Purpose? Education. Optimizations? Yes, I am developing them. Checkout other branches.", "stars": 384, "stars_scraped": 379, "forks": 54, "watchers": 4, "language": "Python", "license": "MIT", "gh_topics": [ "ai", "diffusion-models", "imitation-learning", "robotics", "vision-language-action" ], "pushed_at": "2026-03-17", "created_at": "2025-12-02", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Keivalya Pandya", "owner_company": "", "owner_location": "San Francisco Bay Area, CA", "owner_url": "https://github.com/keivalya", "owner_repos": 95, "owner_followers": 112, "owner_bio": "Robotics engineer who converts caffeine into code \u2615", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Stanford-ILIAD/openvla-mini", "slug": "stanford-iliad-openvla-mini", "url": "https://github.com/Stanford-ILIAD/openvla-mini", "owner": "Stanford-ILIAD", "name": "openvla-mini", "description": "OpenVLA: An open-source vision-language-action model for robotic manipulation.", "readme": "Getting Started | Pretrained VLAs | Installation | Fine-Tuning OpenVLA via LoRA | Fully Fine-Tuning OpenVLA | Training VLAs from Scratch | Evaluating OpenVLA | MiniVLA Details | Action Chunking | Multi-Image | Project Website", "stars": 376, "stars_scraped": 375, "forks": 31, "watchers": 3, "language": null, "license": null, "gh_topics": [], "pushed_at": "2025-03-19", "created_at": "", "archived": false, "paper_ids": [ "2512.22414" ], "owner_type": "Organization", "owner_display": "Stanford Intelligent and Interactive Autonomous Systems Group", "owner_company": "", "owner_location": "Stanford University", "owner_url": "https://github.com/Stanford-ILIAD", "owner_repos": 54, "owner_followers": 263, "owner_bio": "Stanford Intelligent and Interactive Autonomous Systems Group", "affiliated_org": "Stanford", "link_sources": [ "paper-fulltext" ], "papers": [ { "id": "2512.22414", "slug": "emergence-of-human-to-robot-transfer-in-vision-language-action-models", "title": "Emergence of Human to Robot Transfer in Vision-Language-Action Models", "featured": true } ], "topics": [ "vla", "imitation-diffusion" ], "score": 9, "from_paper": false, "link_strength": "mentioned", "stale": false }, { "full_name": "apple/ml-egodex", "slug": "apple-ml-egodex", "url": "https://github.com/apple/ml-egodex", "owner": "apple", "name": "ml-egodex", "description": "EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video", "readme": "The EgoDex dataset is split into a training set, test set, and additional data collected after the 99/1 train/test split was frozen for all experimental results. These have about 725 hours, 7 hours, and 97 hours, respectively. The training set is further divided into 5 zip files for portability. It is easiest to download the test set for initial exploration as it is the smallest zip file. Or, for ", "stars": 375, "stars_scraped": 373, "forks": 13, "watchers": 1, "language": null, "license": null, "gh_topics": [], "pushed_at": "2025-08-20", "created_at": "", "archived": false, "paper_ids": [ "2505.11709" ], "owner_type": "Organization", "owner_display": "Apple", "owner_company": "", "owner_location": "Cupertino, CA", "owner_url": "https://github.com/apple", "owner_repos": 441, "owner_followers": 39692, "owner_bio": "", "affiliated_org": null, "link_sources": [ "paper-fulltext" ], "papers": [ { "id": "2505.11709", "slug": "egodex-learning-dexterous-manipulation-from-large-scale-egocentric-vid", "title": "EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video", "featured": true } ], "topics": [ "dexterous-manipulation", "egocentric-data", "navigation" ], "score": 5, "from_paper": false, "link_strength": "mentioned", "stale": false }, { "full_name": "bytedance/WMP", "slug": "bytedance-wmp", "url": "https://github.com/bytedance/WMP", "owner": "bytedance", "name": "WMP", "description": "Reproduction code of paper \"World Model-based Perception for Visual Legged Locomotion\"", "readme": "Training takes about 23G GPU memory, and at least 10k iterations recommended.", "stars": 372, "stars_scraped": 369, "forks": 35, "watchers": 2, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "research" ], "pushed_at": "2024-12-18", "created_at": "2024-11-26", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Bytedance Inc.", "owner_company": "", "owner_location": "Singapore", "owner_url": "https://github.com/bytedance", "owner_repos": 416, "owner_followers": 18843, "owner_bio": "", "affiliated_org": "ByteDance", "link_sources": [], "papers": [], "topics": [ "world-models", "humanoids" ], "score": 8, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "ucd-dare/CarDreamer", "slug": "ucd-dare-cardreamer", "url": "https://github.com/ucd-dare/CarDreamer", "owner": "ucd-dare", "name": "CarDreamer", "description": "World Model based Autonomous Driving Platform in CARLA :car:", "readme": "Integrating the high-fidelity CARLA simulator with world models, we are able to train a world model that not only learns complex environment dynamics but also have an agent interact with the neural network \"simulator\" to learn to drive.", "stars": 367, "stars_scraped": 366, "forks": 57, "watchers": 5, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "autonomous-driving", "foundation-models", "imitation-learning", "model-based-rl", "reinforcement-learning", "robot-learning", "robotics", "world-models" ], "pushed_at": "2025-12-12", "created_at": "2024-05-12", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "UCD DARE Lab", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/ucd-dare", "owner_repos": 9, "owner_followers": 29, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "sim2real", "navigation" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "MilkClouds/awesome-vla-study", "slug": "milkclouds-awesome-vla-study", "url": "https://github.com/MilkClouds/awesome-vla-study", "owner": "MilkClouds", "name": "awesome-vla-study", "description": "A structured reading list on Vision-Language-Action (VLA) models \u2014 from diffusion/flow matching foundations through state-of-the-art robot foundation model architectures to data scaling, RL fine-tuning, and world models. Papers in reading order.", "readme": "\ud83d\udcce Supplementary video: Stanford CS25 V3 \u2014 Low-level Embodied Intelligence", "stars": 365, "stars_scraped": 360, "forks": 27, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-03-21", "created_at": "2026-02-13", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "MilkClouds", "owner_company": "Seoul National University", "owner_location": "", "owner_url": "https://github.com/MilkClouds", "owner_repos": 50, "owner_followers": 74, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "foundation-pretraining" ], "score": 9, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "ReinFlow/ReinFlow", "slug": "reinflow-reinflow", "url": "https://github.com/ReinFlow/ReinFlow", "owner": "ReinFlow", "name": "ReinFlow", "description": "[NeurIPS 2025] Flow x RL. \"ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning\". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced. ", "readme": "", "stars": 360, "stars_scraped": 359, "forks": 34, "watchers": 7, "language": "Python", "license": "MIT", "gh_topics": [ "actorcritic", "fine-tuning", "finetuning-rl", "finetuning-vision-models", "flow", "flowmatching", "locomotion", "manipulation", "onlinerl", "pi0", "policygradient", "post-training", "rl", "robot-learning", "robotics", "visuomotor", "vla" ], "pushed_at": "2026-04-24", "created_at": "2025-05-29", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "ReinFlow", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/ReinFlow", "owner_repos": 2, "owner_followers": 12, "owner_bio": "Official Repository of the paper: Fine-tuning Flow Matching Policy with Online Reinforcement Learning", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "humanoids", "rl-control" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "NVlabs/alpamayo1.5", "slug": "nvlabs-alpamayo1-5", "url": "https://github.com/NVlabs/alpamayo1.5", "owner": "NVlabs", "name": "alpamayo1.5", "description": "NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced reasoning, navigation guidance, and visual question answering.", "readme": "\ud83d\udce3 Usage questions and discussion about Alpamayo 1.5 : please join us on the Alpamayo NV Developer Forum .", "stars": 355, "stars_scraped": 354, "forks": 77, "watchers": 13, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "alpamayo", "autonomous-driving", "autonomous-vehicles", "chain-of-causation", "end-to-end-driving", "nvidia", "physical-ai", "reasoning", "robotics", "self-driving-car", "trajectory-prediction", "vision-language-action", "visual-question-answering", "vla", "world-models" ], "pushed_at": "2026-08-24", "created_at": "2026-03-03", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "NVIDIA Research Projects", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/NVlabs", "owner_repos": 500, "owner_followers": 11191, "owner_bio": "", "affiliated_org": "NVIDIA", "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "navigation" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Unity-Technologies/Robotics-Object-Pose-Estimation", "slug": "unity-technologies-robotics-object-pose-estimation", "url": "https://github.com/Unity-Technologies/Robotics-Object-Pose-Estimation", "owner": "Unity-Technologies", "name": "Robotics-Object-Pose-Estimation", "description": "A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model is then deployed in a simulated robotic pick-and-place task.", "readme": "Want to skip the tutorial and run the full demo? Check out our Quick Demo .", "stars": 349, "stars_scraped": 348, "forks": 83, "watchers": 12, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "autonomy", "computer-vision", "deep-learning", "machine-learning", "manipulation", "model-training", "motion-planning", "perception", "physics-simulation", "pose-estimation", "robotics", "robotics-simulation", "ros", "simulation", "synthetic-data", "trajectory-generation", "tutorial", "unity", "ur3-robot-arm", "urdf" ], "pushed_at": "2022-04-13", "created_at": "2021-02-19", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Unity Technologies", "owner_company": "", "owner_location": "Copenhagen, Denmark", "owner_url": "https://github.com/Unity-Technologies", "owner_repos": 807, "owner_followers": 12851, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [], "score": 4, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "DerrickXuNu/v2x-vit", "slug": "derrickxunu-v2x-vit", "url": "https://github.com/DerrickXuNu/v2x-vit", "owner": "DerrickXuNu", "name": "v2x-vit", "description": "[ECCV2022] Official Implementation of paper \"V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer\"", "readme": "This is the official implementation of ECCV2022 paper \"V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer\". Runsheng Xu , Hao Xiang , Zhengzhong Tu , Xin Xia , Ming-Hsuan Yang , Jiaqi Ma", "stars": 348, "stars_scraped": 348, "forks": 40, "watchers": 4, "language": null, "license": null, "gh_topics": [ "3d-object-detection", "autonomous-driving", "collaborative-perception", "computer-vision", "deep-learning", "machine-learning", "multi-agent-system", "pytorch", "simulation", "v2x", "vehicle-to-everything", "vision-transformer" ], "pushed_at": "2024-09-06", "created_at": "", "archived": false, "paper_ids": [ "2203.10638" ], "owner_type": "User", "owner_display": "Runsheng Xu", "owner_company": "Waymo @UCLA", "owner_location": "LA", "owner_url": "https://github.com/DerrickXuNu", "owner_repos": 15, "owner_followers": 602, "owner_bio": "Waymo Research Scientist, UCLA PhD.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2203.10638", "slug": "v2x-vit-vehicle-to-everything-cooperative-perception-with-vision-trans", "title": "V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer", "featured": false } ], "topics": [ "video-generation" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "bytedance/fc-clip", "slug": "bytedance-fc-clip", "url": "https://github.com/bytedance/fc-clip", "owner": "bytedance", "name": "fc-clip", "description": "[NeurIPS 2023] This repo contains the code for our paper Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP", "readme": "FC-CLIP is an universal model for open-vocabulary image segmentation problems, consisting of a class-agnostic segmenter, in-vocabulary classifier, out-of-vocabulary classifier. With everything built upon a shared single frozen convolutional CLIP model, FC-CLIP not only achieves state-of-the-art performance on various open-vocabulary segmentation benchmarks, but also enjoys a much lower training (3", "stars": 345, "stars_scraped": 345, "forks": 35, "watchers": 15, "language": null, "license": null, "gh_topics": [ "research" ], "pushed_at": "2024-02-05", "created_at": "", "archived": true, "paper_ids": [ "2308.02487" ], "owner_type": "Organization", "owner_display": "Bytedance Inc.", "owner_company": "", "owner_location": "Singapore", "owner_url": "https://github.com/bytedance", "owner_repos": 416, "owner_followers": 18843, "owner_bio": "", "affiliated_org": "ByteDance", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2308.02487", "slug": "convolutions-die-hard-open-vocabulary-segmentation-with-single-frozen", "title": "Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "OpenDriveLab/RISE", "slug": "opendrivelab-rise", "url": "https://github.com/OpenDriveLab/RISE", "owner": "OpenDriveLab", "name": "RISE", "description": "[RSS 2026] Code for RISE: Self-Improving Robot Policy with Compositional World Model", "readme": "We thank the following projects for their open-source contributions: OpenPI Pi0 / Pi05 , Genie Envisioner , RLinf , LTX-Video , Kai0 .", "stars": 343, "stars_scraped": 341, "forks": 21, "watchers": 4, "language": "Python", "license": null, "gh_topics": [ "diffusion-models", "generative-models", "manipulation", "robot-learning", "value-learning", "vision-language-model", "vla", "world-models" ], "pushed_at": "2026-07-06", "created_at": "2026-02-08", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "OpenDriveLab", "owner_company": "", "owner_location": "Hong Kong", "owner_url": "https://github.com/OpenDriveLab", "owner_repos": 54, "owner_followers": 2675, "owner_bio": "AI for Robotics and Autonomous Driving at The University of Hong Kong (HKU)", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla" ], "score": 8, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "ihmcrobotics/ihmc-open-robotics-software", "slug": "ihmcrobotics-ihmc-open-robotics-software", "url": "https://github.com/ihmcrobotics/ihmc-open-robotics-software", "owner": "ihmcrobotics", "name": "ihmc-open-robotics-software", "description": "Robotics software featuring legged locomotion algorithms and a momentum-based controller core with optimization. Supporting software for world-class robots including humanoids, running birds, exoskeletons, mechs and more.", "readme": "This software has been used to power a wide variety of humanoid robots. This includes", "stars": 325, "stars_scraped": 325, "forks": 110, "watchers": 31, "language": "Java", "license": null, "gh_topics": [ "humanoid-robot", "ihmc", "java", "robotics", "walking", "whole-body-control" ], "pushed_at": "2026-08-26", "created_at": "2016-01-28", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "IHMC Robotics", "owner_company": "", "owner_location": "Pensacola, FL", "owner_url": "https://github.com/ihmcrobotics", "owner_repos": 148, "owner_followers": 152, "owner_bio": "IHMC Robotics Lab on GitHub", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "mihirp1998/VADER", "slug": "mihirp1998-vader", "url": "https://github.com/mihirp1998/VADER", "owner": "mihirp1998", "name": "VADER", "description": "Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various reward models such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics etc. ", "readme": "This is the official implementation of our paper Video Diffusion Alignment via Reward Gradient by", "stars": 318, "stars_scraped": 318, "forks": 15, "watchers": 6, "language": null, "license": null, "gh_topics": [ "alignment", "diffusion", "reinforcement-learning", "reinforcement-learning-human-feedback", "rl", "rlhf", "vader", "video-diffusion", "video-diffusion-alignment" ], "pushed_at": "2025-03-12", "created_at": "", "archived": false, "paper_ids": [ "2407.08737" ], "owner_type": "User", "owner_display": "Mihir Prabhudesai", "owner_company": "", "owner_location": "Pittsburgh", "owner_url": "https://github.com/mihirp1998", "owner_repos": 109, "owner_followers": 62, "owner_bio": "student at CMU", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2407.08737", "slug": "video-diffusion-alignment-via-reward-gradients", "title": "Video Diffusion Alignment via Reward Gradients", "featured": false } ], "topics": [ "world-models", "rl-control", "video-generation" ], "score": 3, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "Genesis-Embodied-AI/DiffTactile", "slug": "genesis-embodied-ai-difftactile", "url": "https://github.com/Genesis-Embodied-AI/DiffTactile", "owner": "Genesis-Embodied-AI", "name": "DiffTactile", "description": "[ICLR 2024] DiffTactile: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation", "readme": "You can create a Conda environment for this simulator:", "stars": 316, "stars_scraped": 316, "forks": 26, "watchers": 5, "language": "Python", "license": "MIT", "gh_topics": [], "pushed_at": "2024-03-20", "created_at": "2024-03-17", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Genesis AI", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Genesis-Embodied-AI", "owner_repos": 16, "owner_followers": 1950, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "tactile", "sim2real" ], "score": 10, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "NathanWu7/isaacLab.manipulation", "slug": "nathanwu7-isaaclab-manipulation", "url": "https://github.com/NathanWu7/isaacLab.manipulation", "owner": "NathanWu7", "name": "isaacLab.manipulation", "description": "An independent extension based on IsaacLab. It provides support for Robot Manipulation tasks (Robot Arm and Dextrous Hand).", "readme": "This template depends on Isaac Sim and IsaacLab.", "stars": 314, "stars_scraped": 314, "forks": 29, "watchers": 1, "language": "Python", "license": "MIT", "gh_topics": [ "isaacgym", "isaaclab", "isaacsim", "manipulation", "robot-learning" ], "pushed_at": "2025-06-29", "created_at": "2024-06-07", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "NathanWu7", "owner_company": "NVIDIA", "owner_location": "", "owner_url": "https://github.com/NathanWu7", "owner_repos": 22, "owner_followers": 77, "owner_bio": "Researcher at Nvidia\r\nPh.D student", "affiliated_org": "NVIDIA", "link_sources": [], "papers": [], "topics": [], "score": 4, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "MINT-SJTU/LeRobot-Anything-U-Arm", "slug": "mint-sjtu-lerobot-anything-u-arm", "url": "https://github.com/MINT-SJTU/LeRobot-Anything-U-Arm", "owner": "MINT-SJTU", "name": "LeRobot-Anything-U-Arm", "description": "U-Arm: Lerobot-Everything-Cross-Embodiment-Teleoperation", "readme": "\ud83d\ude80 Bringing Leader-Follower teleoperation system to every real robot and robot arm -- Cheaper, Smoother, Plug-and-Play \ud83d\udcb5 Starts from $60 cost!! Then controls any robot arm system!!", "stars": 313, "stars_scraped": 313, "forks": 30, "watchers": 5, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2026-07-15", "created_at": "2025-08-17", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "MINT-SJTU", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/MINT-SJTU", "owner_repos": 22, "owner_followers": 175, "owner_bio": "MINT-SJTU: Machine Intelligence and Interaction Lab @ SJTU", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "foundation-pretraining", "data-teleop" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "OpenEnvision/WorldFoundry", "slug": "openenvision-worldfoundry", "url": "https://github.com/OpenEnvision/WorldFoundry", "owner": "OpenEnvision", "name": "WorldFoundry", "description": "Unified World Model Inference & Evaluation Infrastructure", "readme": "WorldFoundry is an open-source infrastructure for world models: a shared stack for in-tree runners, local asset staging, inference (TUI / CLI / Studio), and benchmark evaluation across video generation, 3D/4D representation, embodied action, and interactive worlds.", "stars": 311, "stars_scraped": 309, "forks": 22, "watchers": 0, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "3d", "4d", "benchmark", "evaluation", "inference", "infrastructure", "video-generation", "vla", "wam", "world-model" ], "pushed_at": "2026-07-22", "created_at": "2026-07-09", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "OpenEnvision", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/OpenEnvision", "owner_repos": 11, "owner_followers": 38, "owner_bio": "OpenEnvision is a joint research hub advancing open vision intelligence through academia-industry collaboration.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "video-generation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "mimic-video/mimic-video", "slug": "mimic-video-mimic-video", "url": "https://github.com/mimic-video/mimic-video", "owner": "mimic-video", "name": "mimic-video", "description": "Video-Action Models for Generalizable Robot Control Beyond VLAs", "readme": "mimic-video extracts generalist language-conditioned robot policies (Video-Action Models / VAMs) from pretrained video models by conditioning small action decoders on the video backbones' latent representations. By drawing on the video model's knowledge of real-world dynamics and behaviors, performant action decoders can be learned efficiently and without updating the video model. Employing decoup", "stars": 298, "stars_scraped": 297, "forks": 33, "watchers": 1, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "robot-learning", "robotics", "vam", "video-action-models", "vla" ], "pushed_at": "2026-06-26", "created_at": "2026-04-07", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "mimic-video", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/mimic-video", "owner_repos": 2, "owner_followers": 3, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "flowersteam/Grounding_LLMs_with_online_RL", "slug": "flowersteam-grounding-llms-with-online-rl", "url": "https://github.com/flowersteam/Grounding_LLMs_with_online_RL", "owner": "flowersteam", "name": "Grounding_LLMs_with_online_RL", "description": "We perform functional grounding of LLMs' knowledge in BabyAI-Text", "readme": "We perform functional grounding of LLMs' knowledge in BabyAI-Text using the GLAM method:", "stars": 275, "stars_scraped": 275, "forks": 33, "watchers": 5, "language": null, "license": null, "gh_topics": [ "grounding", "interactive-agents", "language-model", "reinforcement-learning" ], "pushed_at": "2025-10-27", "created_at": "", "archived": false, "paper_ids": [ "2302.02662" ], "owner_type": "Organization", "owner_display": "Flowers Team", "owner_company": "", "owner_location": "Bordeaux / Paris", "owner_url": "https://github.com/flowersteam", "owner_repos": 125, "owner_followers": 98, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2302.02662", "slug": "grounding-large-language-models-in-interactive-environments-with-onlin", "title": "Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "SpesRobotics/teleop", "slug": "spesrobotics-teleop", "url": "https://github.com/SpesRobotics/teleop", "owner": "SpesRobotics", "name": "teleop", "description": "Turns your phone or VR headset into a robot arm teleoperation device by leveraging WebXR", "readme": "Important", "stars": 272, "stars_scraped": 272, "forks": 32, "watchers": 5, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "imitation-learning", "ros2", "teleoperation", "webxr" ], "pushed_at": "2026-07-23", "created_at": "2024-08-21", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Spes Robotics", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/SpesRobotics", "owner_repos": 12, "owner_followers": 33, "owner_bio": "R&D firm for autonomous mobile robots and cobots. System design, machine learning, embedded, and simulation.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "data-teleop" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "PKU-EPIC/UniDexGrasp", "slug": "pku-epic-unidexgrasp", "url": "https://github.com/PKU-EPIC/UniDexGrasp", "owner": "PKU-EPIC", "name": "UniDexGrasp", "description": "Official code for \"UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy\" (CVPR 2023)", "readme": "", "stars": 270, "stars_scraped": 270, "forks": 19, "watchers": 5, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2024-05-25", "created_at": "2023-03-24", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "PKU-EPIC", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/PKU-EPIC", "owner_repos": 37, "owner_followers": 201, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "dexterous-manipulation" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "AILab-CVC/VideoGen-Eval", "slug": "ailab-cvc-videogen-eval", "url": "https://github.com/AILab-CVC/VideoGen-Eval", "owner": "AILab-CVC", "name": "VideoGen-Eval", "description": "VideoGen-Eval: Agent-based System for Video Generation Evaluation", "readme": "Yuhang Yang 1 , Ke Fan 2 , Shangkun Sun 3 , Hongxiang Li 3 , Ailing Zeng 4,* , Feilin Han 5 , Wei Zhai 1,* , Wei Liu 4 , Yang Cao 1 , Zheng-Jun Zha 1", "stars": 269, "stars_scraped": 269, "forks": 14, "watchers": 14, "language": null, "license": null, "gh_topics": [ "aigc", "benchmark", "image-to-video", "sora-video-ai", "text-to-video", "video-evaluation", "video-generation", "video-to-video" ], "pushed_at": "2025-12-16", "created_at": "", "archived": false, "paper_ids": [ "2503.23452" ], "owner_type": "Organization", "owner_display": "TencentAILab-CVC", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/AILab-CVC", "owner_repos": 18, "owner_followers": 699, "owner_bio": "Tencent AI Lab - Computer Vision Center", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2503.23452", "slug": "videogen-eval-agent-based-system-for-video-generation-evaluation", "title": "VideoGen-Eval: Agent-based System for Video Generation Evaluation", "featured": false } ], "topics": [ "video-generation" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "RayYoh/OCRM_survey", "slug": "rayyoh-ocrm-survey", "url": "https://github.com/RayYoh/OCRM_survey", "owner": "RayYoh", "name": "OCRM_survey", "description": "A Survey of Embodied Learning for Object-Centric Robotic Manipulation", "readme": "This is the repository of A Survey of Embodied Learning for Object-Centric Robotic Manipulation , a comprehensive review of latest advancements in object-centric robotic manipulation including embodied perceptual learning, embodied policy learning, and embodied task-oriented learning. For details, please refer to:", "stars": 258, "stars_scraped": 257, "forks": 14, "watchers": 4, "language": null, "license": "MIT", "gh_topics": [ "embodied-ai", "manipulation", "robot-learning", "robotics" ], "pushed_at": "2024-10-04", "created_at": "2024-07-26", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "RayYoh", "owner_company": "PhD@PolyU", "owner_location": "", "owner_url": "https://github.com/RayYoh", "owner_repos": 14, "owner_followers": 40, "owner_bio": "PhD Student", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [], "score": 4, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "SpatialVision/Orient-Anything-V2", "slug": "spatialvision-orient-anything-v2", "url": "https://github.com/SpatialVision/Orient-Anything-V2", "owner": "SpatialVision", "name": "Orient-Anything-V2", "description": "Orient Anything V2, NeurIPS 2025 Spotlight", "readme": "*Equal Contribution", "stars": 251, "stars_scraped": 251, "forks": 10, "watchers": 3, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-01-19", "created_at": "", "archived": false, "paper_ids": [ "2601.05573" ], "owner_type": "Organization", "owner_display": "SpatialVision", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/SpatialVision", "owner_repos": 6, "owner_followers": 42, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2601.05573", "slug": "orient-anything-v2-unifying-orientation-and-rotation-understanding", "title": "Orient Anything V2: Unifying Orientation and Rotation Understanding", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "box2ai-robotics/joycon-robotics", "slug": "box2ai-robotics-joycon-robotics", "url": "https://github.com/box2ai-robotics/joycon-robotics", "owner": "box2ai-robotics", "name": "joycon-robotics", "description": "Joycon-Robotics: Low-Cost, Convenient Teleoperation for One- and Two-Arm Robots", "readme": "", "stars": 245, "stars_scraped": 243, "forks": 35, "watchers": 3, "language": "Jupyter Notebook", "license": "MIT", "gh_topics": [], "pushed_at": "2026-04-12", "created_at": "2025-01-12", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Box2AI Robotics", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/box2ai-robotics", "owner_repos": 9, "owner_followers": 88, "owner_bio": "Box2AI Robotics", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "data-teleop" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "2toinf/UniAct", "slug": "2toinf-uniact", "url": "https://github.com/2toinf/UniAct", "owner": "2toinf", "name": "UniAct", "description": "[CVPR 2025] The offical Implementation of \"Universal Actions for Enhanced Embodied Foundation Models\"", "readme": "we introduce UniAct, a new embodied foundation modeling framework operating in the Universal Action Space. Our learned universal actions capture the generic atomic behaviors across diverse robots by exploiting their shared structural features, and enable enhanced cross-domain data utilization and cross-embodiment generalizations by eliminating the notorious heterogeneity. Moreover, the universal a", "stars": 244, "stars_scraped": 244, "forks": 12, "watchers": 6, "language": "Python", "license": null, "gh_topics": [ "embodied-ai", "foundation-models", "robotics", "universal-actions", "vision-language-action" ], "pushed_at": "2025-11-06", "created_at": "2025-01-14", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Jinliang Zheng", "owner_company": "Tsinghua University", "owner_location": "China", "owner_url": "https://github.com/2toinf", "owner_repos": 18, "owner_followers": 99, "owner_bio": "", "affiliated_org": "Tsinghua", "link_sources": [], "papers": [], "topics": [ "vla", "foundation-pretraining" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Roboparty/UFO", "slug": "roboparty-ufo", "url": "https://github.com/Roboparty/UFO", "owner": "Roboparty", "name": "UFO", "description": "An open-source unsupervised RL framework for humanoid control with FB/TeCH training, robot-aware motion import, and real-world teleoperation.", "readme": "", "stars": 240, "stars_scraped": 228, "forks": 26, "watchers": 2, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "humanoid-control", "mjlab", "teleoperation", "unsupervised-learning" ], "pushed_at": "2026-07-30", "created_at": "2026-07-13", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "RoboParty", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Roboparty", "owner_repos": 48, "owner_followers": 744, "owner_bio": "RoboParty is a company that is changing the world. Our mission is to make our robots serve every household.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "data-teleop" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "SII-FUSC/AME_Locomotion", "slug": "sii-fusc-ame-locomotion", "url": "https://github.com/SII-FUSC/AME_Locomotion", "owner": "SII-FUSC", "name": "AME_Locomotion", "description": "This repository reproduces the Attention-Based Map Encoding (AME) method from the paper Attention-Based Map Encoding for Learning Generalized Legged Locomotion.", "readme": "\u6838\u5fc3\u76ee\u6807\u662f\u57fa\u4e8e\u9ad8\u7a0b\u56fe\u548c\u6ce8\u610f\u529b\u673a\u5236\uff0c\u5b66\u4e60\u5177\u5907\u66f4\u5f3a\u5730\u5f62\u6cdb\u5316\u80fd\u529b\u7684\u817f\u5f0f\u8fd0\u52a8\u7b56\u7565\u3002", "stars": 240, "stars_scraped": 235, "forks": 32, "watchers": 0, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2026-05-05", "created_at": "2026-03-31", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "\u5085\u665f\u7a0b", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/SII-FUSC", "owner_repos": 1, "owner_followers": 0, "owner_bio": "SII is an institution dedicated to innovation in education and research in the field of AI.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "wadeKeith/Awesome-Embodied-AI", "slug": "wadekeith-awesome-embodied-ai", "url": "https://github.com/wadeKeith/Awesome-Embodied-AI", "owner": "wadeKeith", "name": "Awesome-Embodied-AI", "description": "Curated embodied AI list: surveys, VLA models, datasets, simulators, humanoids, robot learning, and safety resources.", "readme": "", "stars": 240, "stars_scraped": 239, "forks": 13, "watchers": 4, "language": "Python", "license": "MIT", "gh_topics": [ "awesome-list", "datasets", "embodied-ai", "humanoid-robotics", "physical-ai", "reinforcement-learning", "robot-learning", "robot-manipulation", "robotics", "safety", "simulators", "vision-language-action" ], "pushed_at": "2026-08-26", "created_at": "2025-03-17", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Cheng Yin", "owner_company": "THUNLP", "owner_location": "Beijing", "owner_url": "https://github.com/wadeKeith", "owner_repos": 42, "owner_followers": 84, "owner_bio": "I am a Ph.D student at HUST, China. Joint training with Tsinghua University @thunlp . Embodied intelligence field, RL field. Worked @OpenBMB(ModelBest).", "affiliated_org": "Tsinghua", "link_sources": [], "papers": [], "topics": [ "vla", "humanoids", "sim2real", "safety-eval" ], "score": 12, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "OpenDriveLab/EgoHumanoid", "slug": "opendrivelab-egohumanoid", "url": "https://github.com/OpenDriveLab/EgoHumanoid", "owner": "OpenDriveLab", "name": "EgoHumanoid", "description": "[RSS 2026] The first framework enabling humanoid robots to learn whole-body loco-manipulation from egocentric human demos", "readme": "Human demonstrations offer rich environmental diversity and scale naturally, making them an appealing alternative to robot teleoperation. We present EGOHUMANOID, the first framework to co-train a vision-language-action policy using abundant egocentric human demonstrations together with a limited amount of robot data.", "stars": 237, "stars_scraped": 234, "forks": 8, "watchers": 2, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "egocentric-data", "embodied-ai", "humanoid-robot", "loco-manipulation" ], "pushed_at": "2026-06-06", "created_at": "2026-02-04", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "OpenDriveLab", "owner_company": "", "owner_location": "Hong Kong", "owner_url": "https://github.com/OpenDriveLab", "owner_repos": 54, "owner_followers": 2675, "owner_bio": "AI for Robotics and Autonomous Driving at The University of Hong Kong (HKU)", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "humanoids", "egocentric-data", "data-teleop" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "stephane-caron/pymanoid", "slug": "stephane-caron-pymanoid", "url": "https://github.com/stephane-caron/pymanoid", "owner": "stephane-caron", "name": "pymanoid", "description": "Humanoid robotics prototyping environment based on OpenRAVE", "readme": "\u26a0\ufe0f This project is archived . Feel free to look at the code, but don't expect support to install and run it.", "stars": 233, "stars_scraped": 233, "forks": 39, "watchers": 2, "language": "Python", "license": "GPL-3.0", "gh_topics": [ "humanoid-robot", "inverse-kinematics", "locomotion", "model-predictive-control", "openrave", "python", "robotics" ], "pushed_at": "2024-02-19", "created_at": "2015-06-30", "archived": true, "paper_ids": [], "owner_type": "User", "owner_display": "St\u00e9phane Caron", "owner_company": "CNRS", "owner_location": "Paris", "owner_url": "https://github.com/stephane-caron", "owner_repos": 62, "owner_followers": 882, "owner_bio": "Likes open-source robots.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "ros-teleop/teleop_tools", "slug": "ros-teleop-teleop-tools", "url": "https://github.com/ros-teleop/teleop_tools", "owner": "ros-teleop", "name": "teleop_tools", "description": "A set of generic teleoperation tools for any robot.", "readme": "", "stars": 232, "stars_scraped": 232, "forks": 166, "watchers": 7, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2026-01-27", "created_at": "2013-10-02", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "ros-teleop", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/ros-teleop", "owner_repos": 5, "owner_followers": 52, "owner_bio": "Packages especially for teleoperating ROS robots", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "data-teleop" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "ai4ce/CityWalker", "slug": "ai4ce-citywalker", "url": "https://github.com/ai4ce/CityWalker", "owner": "ai4ce", "name": "CityWalker", "description": "[CVPR2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos", "readme": "", "stars": 229, "stars_scraped": 228, "forks": 13, "watchers": 5, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "cvpr2025", "embodied-ai", "embodied-navigation", "imitation-learning", "outdoor-navigation", "point-goal-navigation", "quadruped", "robot-learning", "scaling-law", "urban-navigation", "video-learning", "visual-navigation" ], "pushed_at": "2025-09-19", "created_at": "2024-10-07", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "AI4CE Lab @ NYU", "owner_company": "", "owner_location": "Brooklyn, NY, U.S.", "owner_url": "https://github.com/ai4ce", "owner_repos": 66, "owner_followers": 282, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "navigation" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "LostXine/LLaRA", "slug": "lostxine-llara", "url": "https://github.com/LostXine/LLaRA", "owner": "LostXine", "name": "LLaRA", "description": "[ICLR'25] LLaRA: Supercharging Robot Learning Data for Vision-Language Policy", "readme": "Xiang Li 1 , Cristina Mata 1 , Jongwoo Park 1 , Kumara Kahatapitiya 1 , Yoo Sung Jang 1 , Jinghuan Shang 1 , Kanchana Ranasinghe 1 , Ryan Burgert 1 , Mu Cai 2 , Yong Jae Lee 2 , and Michael S. Ryoo 1", "stars": 228, "stars_scraped": 228, "forks": 8, "watchers": 6, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "behavioral-cloning", "iclr", "iclr2025", "instruction-tuning", "llava", "robotics", "self-supervised-learning", "vla", "vlm" ], "pushed_at": "2025-03-29", "created_at": "2024-06-07", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Xiang Li", "owner_company": "Stony Brook University", "owner_location": "Stony Brook, NY", "owner_url": "https://github.com/LostXine", "owner_repos": 32, "owner_followers": 106, "owner_bio": "Ph.D. candidate. Used to be young, sometimes simple, always naive.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "BridgeVLA/BridgeVLA", "slug": "bridgevla-bridgevla", "url": "https://github.com/BridgeVLA/BridgeVLA", "owner": "BridgeVLA", "name": "BridgeVLA", "description": "\u2728\u2728Official implementation of BridgeVLA and BridgeVLA++", "readme": "", "stars": 220, "stars_scraped": 219, "forks": 20, "watchers": 2, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "3d-manipulation", "embodied-ai", "robotics", "vision-language-action", "vision-language-pretraining" ], "pushed_at": "2026-08-13", "created_at": "2025-06-09", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "BridgeVLA", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/BridgeVLA", "owner_repos": 2, "owner_followers": 8, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "foundation-pretraining" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "LeCAR-Lab/SPI-Active", "slug": "lecar-lab-spi-active", "url": "https://github.com/LeCAR-Lab/SPI-Active", "owner": "LeCAR-Lab", "name": "SPI-Active", "description": "Official Implementation of \"Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning\"", "readme": "SPI-Active is a sampling-based System Identification (SysID) framework for legged robots , designed with active exploration to identify parameters of legged robots and therby reducing sim2real gap. This codebase implements the approach published in our CoRL 2025 paper.", "stars": 217, "stars_scraped": 216, "forks": 8, "watchers": 10, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2025-11-26", "created_at": "2025-05-15", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "LeCAR Lab at CMU", "owner_company": "", "owner_location": "United States of America", "owner_url": "https://github.com/LeCAR-Lab", "owner_repos": 28, "owner_followers": 872, "owner_bio": "Learning and Control for Agile Robotics Lab at CMU", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real", "navigation" ], "score": 9, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "inspirai/MetalHead", "slug": "inspirai-metalhead", "url": "https://github.com/inspirai/MetalHead", "owner": "inspirai", "name": "MetalHead", "description": "Natural Locomotion, Jumping and Recovery of Quadruped Robot A1 with AMP", "readme": "This repository is based off of Alejandro Escontrela's AMP_for_hardware . All experiments are running with A1 robot from Unitree on Isaac Gym .", "stars": 216, "stars_scraped": 215, "forks": 15, "watchers": 2, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "imitation-learning", "isaac-gym", "quadruped-robot", "reinforcement-learning", "robot-learning" ], "pushed_at": "2023-05-12", "created_at": "2023-04-28", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "inspir.ai", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/inspirai", "owner_repos": 7, "owner_followers": 54, "owner_bio": " Inspir.ai is a tech company focusing on Artificial General Intelligence, committed to creating extraordinary AI Beings for the Metaverse.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 7, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "jayLEE0301/vq_bet_official", "slug": "jaylee0301-vq-bet-official", "url": "https://github.com/jayLEE0301/vq_bet_official", "owner": "jayLEE0301", "name": "vq_bet_official", "description": "Official code for \"Behavior Generation with Latent Actions\" (ICML 2024 Spotlight)", "readme": "Make a conda environemnt (We tested on python 3.7 and 3.9) and activate the environment", "stars": 214, "stars_scraped": 214, "forks": 22, "watchers": 3, "language": null, "license": null, "gh_topics": [ "imitation-learning", "robotics" ], "pushed_at": "2024-02-28", "created_at": "", "archived": false, "paper_ids": [ "2403.03181" ], "owner_type": "User", "owner_display": "Seungjae Lee", "owner_company": "University of Maryland", "owner_location": "Maryland, College Park", "owner_url": "https://github.com/jayLEE0301", "owner_repos": 13, "owner_followers": 59, "owner_bio": "Ph.D. student at UMD CS / \r\nprev @ NYU, SNU, TRI", "affiliated_org": "Toyota Research Institute", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2403.03181", "slug": "behavior-generation-with-latent-actions", "title": "Behavior Generation with Latent Actions", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "likenneth/othello_world", "slug": "likenneth-othello-world", "url": "https://github.com/likenneth/othello_world", "owner": "likenneth", "name": "othello_world", "description": "Emergent world representations: Exploring a sequence model trained on a synthetic task ", "readme": "Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics, or do they rely on internal representations of the process that generates the sequences they see? We investigate this question by applying a variant of the GPT model to the task of predicting legal moves in a simple boa", "stars": 214, "stars_scraped": 214, "forks": 55, "watchers": 5, "language": null, "license": null, "gh_topics": [], "pushed_at": "2023-07-12", "created_at": "", "archived": false, "paper_ids": [ "2210.13382" ], "owner_type": "User", "owner_display": "Kenneth Li", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/likenneth", "owner_repos": 10, "owner_followers": 61, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2210.13382", "slug": "emergent-world-representations-exploring-a-sequence-model-trained-on-a", "title": "Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "DexForce/EmbodiChain", "slug": "dexforce-embodichain", "url": "https://github.com/DexForce/EmbodiChain", "owner": "DexForce", "name": "EmbodiChain", "description": "An end-to-end, GPU-accelerated, and modular platform for building generalized Embodied Intelligence.", "readme": "Note", "stars": 212, "stars_scraped": 212, "forks": 21, "watchers": 2, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "agents", "data-generation", "embodied-ai", "generative-simulation", "gpu-acceleration", "motion-generation", "physics-simulation", "real2sim", "robot-learning", "robotics", "sim2real" ], "pushed_at": "2026-08-26", "created_at": "2025-10-24", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "DexForce", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/DexForce", "owner_repos": 4, "owner_followers": 18, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Beckschen/ViTamin", "slug": "beckschen-vitamin", "url": "https://github.com/Beckschen/ViTamin", "owner": "Beckschen", "name": "ViTamin", "description": "[CVPR 2024] Official implementation of \"ViTamin: Designing Scalable Vision Models in the Vision-language Era\"", "readme": "ViTamin-XL, with only 436M parameters and trained on the public DataComp-1B dataset, achieves an impressive 82.9% zero-shot ImageNet accuracy.", "stars": 211, "stars_scraped": 211, "forks": 6, "watchers": 7, "language": null, "license": null, "gh_topics": [ "scalable-vision-encoder", "vlms" ], "pushed_at": "2024-06-09", "created_at": "", "archived": false, "paper_ids": [ "2404.02132" ], "owner_type": "User", "owner_display": "Jieneng Chen", "owner_company": "Johns Hopkins University", "owner_location": "", "owner_url": "https://github.com/Beckschen", "owner_repos": 12, "owner_followers": 280, "owner_bio": "Dedicated to open-source communities.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2404.02132", "slug": "vitamin-designing-scalable-vision-models-in-the-vision-language-era", "title": "ViTamin: Designing Scalable Vision Models in the Vision-Language Era", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "NVlabs/alpamayo2", "slug": "nvlabs-alpamayo2", "url": "https://github.com/NVlabs/alpamayo2", "owner": "NVlabs", "name": "alpamayo2", "description": "NVIDIA Alpamayo 2 Super is an open 34B multi-task foundation model designed to supercharge autonomous vehicle development.", "readme": "", "stars": 208, "stars_scraped": 203, "forks": 32, "watchers": 0, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "alpamayo", "autonomous-driving", "autonomous-vehicles", "chain-of-causation", "end-to-end-driving", "foundation-model", "nvidia", "physical-ai", "reasoning", "robotics", "self-driving-car", "trajectory-prediction", "vision-language-action", "vla", "world-models" ], "pushed_at": "2026-08-05", "created_at": "2026-05-28", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "NVIDIA Research Projects", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/NVlabs", "owner_repos": 500, "owner_followers": 11191, "owner_bio": "", "affiliated_org": "NVIDIA", "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "foundation-pretraining" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "apexrl/awesome-rl-for-legged-locomotion", "slug": "apexrl-awesome-rl-for-legged-locomotion", "url": "https://github.com/apexrl/awesome-rl-for-legged-locomotion", "owner": "apexrl", "name": "awesome-rl-for-legged-locomotion", "description": "A curated list of awesome material on legged robot locomotion using reinforcement learning (RL) and sim-to-real techniques.", "readme": "Focus on real-world deployment : Techniques to bridge the sim2real gap, including domain randomization, motor modeling, and online adaptation.", "stars": 206, "stars_scraped": 203, "forks": 17, "watchers": 7, "language": null, "license": "CC0-1.0", "gh_topics": [ "awesome", "humanoid-robot", "locomotion", "quadruped", "reinforcement-learning" ], "pushed_at": "2025-03-28", "created_at": "2025-03-25", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "ApexRL", "owner_company": "", "owner_location": "Shanghai Jiao Tong University, China", "owner_url": "https://github.com/apexrl", "owner_repos": 21, "owner_followers": 126, "owner_bio": "RL group @ ApexLab in SJTU. Focusing on reinforcement learning, imitation learning and robotics.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real", "rl-control" ], "score": 13, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "zengweishuai/ScaleBFM", "slug": "zengweishuai-scalebfm", "url": "https://github.com/zengweishuai/ScaleBFM", "owner": "zengweishuai", "name": "ScaleBFM", "description": "The official implementation of the paper \"Scaling Behavior Foundation Model for Humanoid Robots\"", "readme": "", "stars": 203, "stars_scraped": 209, "forks": 8, "watchers": 3, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2026-07-25", "created_at": "2026-07-16", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Weishuai Zeng", "owner_company": "Peking University", "owner_location": "Peking, China", "owner_url": "https://github.com/zengweishuai", "owner_repos": 2, "owner_followers": 40, "owner_bio": "", "affiliated_org": "Peking University", "link_sources": [], "papers": [], "topics": [ "humanoids", "foundation-pretraining" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Rhoban/microban", "slug": "rhoban-microban", "url": "https://github.com/Rhoban/microban", "owner": "Rhoban", "name": "microban", "description": "Microban is an affordable, fully 3D-printable, and 100% open-source humanoid robot. Powered by a Raspberry Pi Zero 2W and 19 Dynamixel servomotors, it serves as an accessible DIY platform for learning, experimentation, and research in robotics.", "readme": "Welcome to the Microban project!", "stars": 202, "stars_scraped": 160, "forks": 25, "watchers": 5, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "diy", "electronics", "engineering", "humanoid-robot", "robotics" ], "pushed_at": "2026-07-21", "created_at": "2026-05-06", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Rhoban", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Rhoban", "owner_repos": 98, "owner_followers": 118, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Taccel-Simulator/Taccel", "slug": "taccel-simulator-taccel", "url": "https://github.com/Taccel-Simulator/Taccel", "owner": "Taccel-Simulator", "name": "Taccel", "description": "Taccel: Scaling-up Vision-based Tactile Robotics with High-performance GPU Simulation", "readme": "* Equal Contributor \u2020 Corresponding Author", "stars": 199, "stars_scraped": 199, "forks": 16, "watchers": 8, "language": "Cuda", "license": "MIT", "gh_topics": [ "nvidia-warp", "robotics", "simulation", "tactile", "warp" ], "pushed_at": "2025-10-13", "created_at": "2025-03-28", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Taccel Simulator", "owner_company": "", "owner_location": "China", "owner_url": "https://github.com/Taccel-Simulator", "owner_repos": 2, "owner_followers": 18, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "tactile", "sim2real" ], "score": 8, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "carlosferrazza/BodyTransformer", "slug": "carlosferrazza-bodytransformer", "url": "https://github.com/carlosferrazza/BodyTransformer", "owner": "carlosferrazza", "name": "BodyTransformer", "description": "Body Transformer: Leveraging Robot Embodiment for Policy Learning", "readme": "", "stars": 199, "stars_scraped": 199, "forks": 16, "watchers": 5, "language": "Jupyter Notebook", "license": "NOASSERTION", "gh_topics": [], "pushed_at": "2025-09-18", "created_at": "2024-08-13", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Carlo Sferrazza", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/carlosferrazza", "owner_repos": 12, "owner_followers": 73, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "HybridRobotics/DiffuseLoco", "slug": "hybridrobotics-diffuseloco", "url": "https://github.com/HybridRobotics/DiffuseLoco", "owner": "HybridRobotics", "name": "DiffuseLoco", "description": "Source code for the paper DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets", "readme": "Paper / Project Page", "stars": 198, "stars_scraped": 197, "forks": 25, "watchers": 8, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2025-04-14", "created_at": "2024-10-14", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Hybrid Robotics", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/HybridRobotics", "owner_repos": 41, "owner_followers": 861, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "H-Freax/Awesome-Video-Robotic-Papers", "slug": "h-freax-awesome-video-robotic-papers", "url": "https://github.com/H-Freax/Awesome-Video-Robotic-Papers", "owner": "H-Freax", "name": "Awesome-Video-Robotic-Papers", "description": "This repository compiles a list of papers related to the application of video technology in the field of robotics! Star\u2b50 the repo and follow me if you like what you see\ud83e\udd29.", "readme": "Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation", "stars": 193, "stars_scraped": 193, "forks": 5, "watchers": 5, "language": null, "license": null, "gh_topics": [ "artificial-intelligence", "awesome-list", "list", "manipulation", "paper", "robot", "robot-arm", "robot-arm-control", "robot-learning", "robotics", "video" ], "pushed_at": "2025-01-30", "created_at": "2024-06-18", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Freax Ruby", "owner_company": "Northeastern University", "owner_location": "Boston", "owner_url": "https://github.com/H-Freax", "owner_repos": 42, "owner_followers": 144, "owner_bio": "\ud83d\udc31\ud83d\udc36\ud83d\udc2f\ud83e\udd81\ud83e\udd8b", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [], "score": 4, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "Renforce-Dynamics/MultiModalWBC", "slug": "renforce-dynamics-multimodalwbc", "url": "https://github.com/Renforce-Dynamics/MultiModalWBC", "owner": "Renforce-Dynamics", "name": "MultiModalWBC", "description": "MultiModalWBC is a fully open-source, IsaacLab-based framework for multi-modal whole-body control, designed for motion imitation, motion tracking, and task-conditioned control in legged robots. The framework unifies robot proprioceptive states and multi-modal human motion conditions into a consistent interface", "readme": "", "stars": 192, "stars_scraped": 190, "forks": 11, "watchers": 2, "language": "Python", "license": null, "gh_topics": [ "humanoid-robot", "issaclab", "reinforcement-learning", "robotics", "simulations" ], "pushed_at": "2026-06-16", "created_at": "2026-02-09", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Renforce Dynamics", "owner_company": "", "owner_location": "China", "owner_url": "https://github.com/Renforce-Dynamics", "owner_repos": 29, "owner_followers": 146, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "rigbetellabs/tortoisebot", "slug": "rigbetellabs-tortoisebot", "url": "https://github.com/rigbetellabs/tortoisebot", "owner": "rigbetellabs", "name": "tortoisebot", "description": "TortoiseBot is an extremely learner-friendly and cost-efficient ROS-based Open-sourced Mobile Robot that is capable of doing Teleoperation, Manual as well as Autonomous Mapping, Navigation, Simulation, etc.", "readme": "", "stars": 189, "stars_scraped": 189, "forks": 68, "watchers": 11, "language": "Makefile", "license": null, "gh_topics": [ "galactic", "gazebo", "humble", "jazzy", "navigation", "robot", "robotics", "ros", "ros2", "slam", "turtlebot", "turtlebot3" ], "pushed_at": "2026-08-05", "created_at": "2021-02-07", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "RigBetel Labs LLP", "owner_company": "", "owner_location": "Pune, MH, India", "owner_url": "https://github.com/rigbetellabs", "owner_repos": 50, "owner_followers": 85, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "spatial-3d", "navigation", "data-teleop" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "zhouxian/act3d-chained-diffuser", "slug": "zhouxian-act3d-chained-diffuser", "url": "https://github.com/zhouxian/act3d-chained-diffuser", "owner": "zhouxian", "name": "act3d-chained-diffuser", "description": "A unified architecture for multimodal multi-task robotic policy learning.", "readme": "Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation Theophile Gervet* , Zhou Xian* , Nikolaos Gkanatsios , Katerina Fragkiadaki", "stars": 186, "stars_scraped": 186, "forks": 14, "watchers": 2, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2024-02-02", "created_at": "2023-06-27", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Zhou Xian", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/zhouxian", "owner_repos": 16, "owner_followers": 590, "owner_bio": "PhD student in Robotics & AI @ CMU.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [], "score": 4, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "AndrejOrsula/space_robotics_bench", "slug": "andrejorsula-space-robotics-bench", "url": "https://github.com/AndrejOrsula/space_robotics_bench", "owner": "AndrejOrsula", "name": "space_robotics_bench", "description": "Robot Learning Beyond Earth", "readme": "Space Robotics Bench (SRB) is a comprehensive collection of environments and tasks for robotics research in the challenging domain of space. It provides a unified framework for developing and validating autonomous systems under diverse extraterrestrial scenarios. At the same time, its design is flexible and extensible to accommodate a variety of development workflows and research directions beyond", "stars": 183, "stars_scraped": 183, "forks": 27, "watchers": 5, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "benchmark", "robot-learning", "robotics", "simulation", "space", "space-robotics", "space-ros" ], "pushed_at": "2025-12-01", "created_at": "2024-10-21", "archived": false, "paper_ids": [ "2608.23452" ], "owner_type": "User", "owner_display": "Andrej Orsula", "owner_company": "snt-spacer", "owner_location": "Luxembourg", "owner_url": "https://github.com/AndrejOrsula", "owner_repos": 79, "owner_followers": 219, "owner_bio": "Robot Learning in Space", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.23452", "slug": "reward-free-continual-adaptation-for-resilient-space-robots", "title": "Reward-Free Continual Adaptation for Resilient Space Robots", "featured": false } ], "topics": [], "score": 2, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "Open-X-Humanoid/XR-1", "slug": "open-x-humanoid-xr-1", "url": "https://github.com/Open-X-Humanoid/XR-1", "owner": "Open-X-Humanoid", "name": "XR-1", "description": "Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations", "readme": "Shichao Fan 1,* , Kun Wu 1,* , Zhengping Che 1,*,\u2020 , Xinhua Wang 1 , Di Wu 1,4 , Fei Liao 1 , Ning Liu 1 , Yixue Zhang 1 , Zhen Zhao 1 , Zhiyuan Xu 1 , Meng Li 1 , Qingjie Liu 3 , Shanghang Zhang 4 , Min Wan 2 , Jian Tang 1,\u2709", "stars": 182, "stars_scraped": 179, "forks": 23, "watchers": 8, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "diffusion-policy", "embodied-ai", "foundation-models", "vision-language-action", "vla-model" ], "pushed_at": "2026-07-16", "created_at": "2025-12-18", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Open X-Humanoid", "owner_company": "", "owner_location": "\u4e2d\u56fd", "owner_url": "https://github.com/Open-X-Humanoid", "owner_repos": 24, "owner_followers": 415, "owner_bio": "the first innovation center in China that focuses on the core technology, product development, and application ecosystem construction of humanoid robots.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "humanoids" ], "score": 8, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "cvlab-kaist/Geometric-Action-Model", "slug": "cvlab-kaist-geometric-action-model", "url": "https://github.com/cvlab-kaist/Geometric-Action-Model", "owner": "cvlab-kaist", "name": "Geometric-Action-Model", "description": "Official implementation of \"Geometric Action Model for Robot Policy Learning\"", "readme": "* Equal contribution. \u2020 Co-corresponding authors.", "stars": 180, "stars_scraped": 179, "forks": 4, "watchers": 5, "language": "Python", "license": "NOASSERTION", "gh_topics": [], "pushed_at": "2026-08-23", "created_at": "2026-06-10", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "cvlab-kaist", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/cvlab-kaist", "owner_repos": 90, "owner_followers": 223, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "jiachengliu3/OpenWBC", "slug": "jiachengliu3-openwbc", "url": "https://github.com/jiachengliu3/OpenWBC", "owner": "jiachengliu3", "name": "OpenWBC", "description": "VR-based Robot Teleoperation and Data Collection System for Humanoid Whole-Body VLA (Unitree G1)", "readme": "This project implements whole-body control for the Unitree G1 robot: using Apple Vision Pro with avp_teleoperate to control the robot's upper body and the OpenHomie algorithm to control lower body movement. It also supports whole-body data collection functionality.", "stars": 174, "stars_scraped": 174, "forks": 9, "watchers": 1, "language": "C++", "license": null, "gh_topics": [], "pushed_at": "2026-02-17", "created_at": "2025-05-22", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "jiachengliu3(SII)", "owner_company": "Shanghai Innovation Institute", "owner_location": "Shanghai", "owner_url": "https://github.com/jiachengliu3", "owner_repos": 20, "owner_followers": 19, "owner_bio": "WLU & ZJU & SII PhD student.\r\n(SII is an institution dedicated to innovation in education and research in the field of AI.)", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "humanoids", "data-teleop" ], "score": 9, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "InternRobotics/Re3Sim", "slug": "internrobotics-re3sim", "url": "https://github.com/InternRobotics/Re3Sim", "owner": "InternRobotics", "name": "Re3Sim", "description": "[ICRA 2026] Re3Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation", "readme": "Install IsaacLab:v1.1.0", "stars": 173, "stars_scraped": 172, "forks": 9, "watchers": 3, "language": "Jupyter Notebook", "license": null, "gh_topics": [ "manipulation", "robotics", "sim-to-real" ], "pushed_at": "2026-03-16", "created_at": "2025-02-12", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Intern Robotics", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/InternRobotics", "owner_repos": 88, "owner_followers": 1805, "owner_bio": "Building inclusive infrastructure for Embodied AI, from Shanghai AI Lab.", "affiliated_org": "Shanghai AI Lab", "link_sources": [], "papers": [], "topics": [ "sim2real" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "BotRunner64/Teleopit", "slug": "botrunner64-teleopit", "url": "https://github.com/BotRunner64/Teleopit", "owner": "BotRunner64", "name": "Teleopit", "description": "a full-embodiment humanoid teleoperation system", "readme": "Project Homepage \u2022 Documentation \u2022 \u4e2d\u6587\u6587\u6863", "stars": 172, "stars_scraped": 171, "forks": 10, "watchers": 2, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "humanoid-robot", "teleoperation" ], "pushed_at": "2026-08-10", "created_at": "2026-02-20", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Wu Bingqian \u5434\u79c9\u8c26", "owner_company": "Westlake University", "owner_location": "China Zhejiang Hangzhou", "owner_url": "https://github.com/BotRunner64", "owner_repos": 27, "owner_followers": 68, "owner_bio": "robotics developer", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "data-teleop" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "worldbench/awesome-embodied-data-pyramid", "slug": "worldbench-awesome-embodied-data-pyramid", "url": "https://github.com/worldbench/awesome-embodied-data-pyramid", "owner": "worldbench", "name": "awesome-embodied-data-pyramid", "description": "\ud83d\udd25 Data Pyramid for Embodied Manipulation: A Survey", "readme": "This repository accompanies a survey on the data pyramid for robotics and embodied AI. It curates the datasets, data-collection paradigms, simulators, and data-hungry model families reviewed in the survey \u2014 spanning real-robot data , UMI (in-the-wild) data , egocentric / ego-exo human data , simulation data , and broad general (web-scale) data \u2014 together with the VLA / world-action / embodied-VLM ", "stars": 172, "stars_scraped": 160, "forks": 3, "watchers": 3, "language": "HTML", "license": "Apache-2.0", "gh_topics": [ "3d", "4d", "data", "data-collection", "egocentric-vision", "embodied-agent", "embodied-ai", "embodied-intelligence", "manipulation", "real2sim", "real2sim2real", "robotics", "sensor", "sim2real", "simulation", "umi", "vision-language", "vision-language-action", "world-modeling" ], "pushed_at": "2026-08-26", "created_at": "2026-07-14", "archived": false, "paper_ids": [ "2607.24744" ], "owner_type": "Organization", "owner_display": "worldbench", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/worldbench", "owner_repos": 29, "owner_followers": 148, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.24744", "slug": "data-pyramid-for-embodied-manipulation-a-survey", "title": "Data Pyramid for Embodied Manipulation: A Survey", "featured": false } ], "topics": [ "world-models", "vla", "egocentric-data", "sim2real", "data-teleop" ], "score": 10, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "emNavi/AirGym", "slug": "emnavi-airgym", "url": "https://github.com/emNavi/AirGym", "owner": "emNavi", "name": "AirGym", "description": "A high-performance drone deep reinforcement learning platform built upon IsaacGym.", "readme": "v0.5.1 released on 2025.09.27: Fix bugs: planning task resets at start when loading trained model planning_cnn_rate.pth .", "stars": 171, "stars_scraped": 170, "forks": 15, "watchers": 4, "language": "Python", "license": "BSD-3-Clause", "gh_topics": [ "drl-pytorch", "quadrotor-simulation", "robot-learning", "sim-to-real" ], "pushed_at": "2026-08-04", "created_at": "2024-03-02", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "emNavi", "owner_company": "", "owner_location": "China", "owner_url": "https://github.com/emNavi", "owner_repos": 23, "owner_followers": 91, "owner_bio": "\u8d85\u5fae\u667a\u5bfc\u6280\u672f\u56e2\u961f FROM \u6e05\u534e\u5927\u5b66", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real", "rl-control", "navigation" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "robocurve/inspect-robots", "slug": "robocurve-inspect-robots", "url": "https://github.com/robocurve/inspect-robots", "owner": "robocurve", "name": "inspect-robots", "description": "Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.", "readme": "", "stars": 167, "stars_scraped": 161, "forks": 21, "watchers": 1, "language": "Python", "license": "MIT", "gh_topics": [ "benchmark", "embodied-ai", "evaluation", "physical-ai", "rerun", "robotics", "vision-language-action", "vla" ], "pushed_at": "2026-08-20", "created_at": "2026-06-26", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "robocurve", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/robocurve", "owner_repos": 13, "owner_followers": 38, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "humanoids" ], "score": 8, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "lihzha/lap", "slug": "lihzha-lap", "url": "https://github.com/lihzha/lap", "owner": "lihzha", "name": "lap", "description": "LAP: Language-Action Pre-Training Enables Zero-Shot Cross Embodiment Transfer", "readme": "If you already cloned the repository without submodules:", "stars": 166, "stars_scraped": 165, "forks": 20, "watchers": 3, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "cross-embodiment", "robot-learning", "vision-language-action-model" ], "pushed_at": "2026-05-20", "created_at": "2026-02-04", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Lihan Zha", "owner_company": "Princeton University", "owner_location": "United States", "owner_url": "https://github.com/lihzha", "owner_repos": 31, "owner_followers": 34, "owner_bio": "Robotics PhD @Princeton", "affiliated_org": "Princeton", "link_sources": [], "papers": [], "topics": [ "vla", "foundation-pretraining" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "valeoai/VideoActionModel", "slug": "valeoai-videoactionmodel", "url": "https://github.com/valeoai/VideoActionModel", "owner": "valeoai", "name": "VideoActionModel", "description": "VaViM and VaVAM: Autonomous Driving through Video Generative Modeling (official repository).", "readme": "We explores the potential of large-scale generative video models to enhance autonomous driving capabilities, introducing an open-source autoregressive video model (VaViM) and a companion video-action model (VaVAM). VaViM is a simple autoregressive model that predicts frames using spatio-temporal token sequences, while VaVAM leverages the learned representations to generate driving trajectories thr", "stars": 165, "stars_scraped": 165, "forks": 9, "watchers": 6, "language": null, "license": null, "gh_topics": [ "autonomous-driving", "mobile-robots", "video-generation", "world-models" ], "pushed_at": "2025-07-03", "created_at": "", "archived": false, "paper_ids": [ "2502.15672" ], "owner_type": "Organization", "owner_display": "valeo.ai", "owner_company": "", "owner_location": "Paris, France", "owner_url": "https://github.com/valeoai", "owner_repos": 90, "owner_followers": 358, "owner_bio": "We are an international team based in Paris, conducting AI research for Valeo automotive applications, in collaboration with world-class academics.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2502.15672", "slug": "vavim-and-vavam-autonomous-driving-through-video-generative-modeling", "title": "VaViM and VaVAM: Autonomous Driving through Video Generative Modeling", "featured": false } ], "topics": [ "world-models", "navigation", "video-generation" ], "score": 2, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "philfung/awesome-reliable-robotics", "slug": "philfung-awesome-reliable-robotics", "url": "https://github.com/philfung/awesome-reliable-robotics", "owner": "philfung", "name": "awesome-reliable-robotics", "description": "Robotics research demonstrating reliability and robustness in the real world (continuously updated)", "readme": "", "stars": 163, "stars_scraped": 161, "forks": 9, "watchers": 13, "language": null, "license": "MIT", "gh_topics": [ "fine-tuning", "imitation-learning", "manipulation", "manipulator-robotics", "reinforcement-learning", "reward-shaping", "robotic-arm", "robotics", "robots", "vision-language-model", "vla", "world-models" ], "pushed_at": "2026-07-21", "created_at": "2025-05-22", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Philip Fung", "owner_company": "", "owner_location": "San Francisco, CA", "owner_url": "https://github.com/philfung", "owner_repos": 51, "owner_followers": 125, "owner_bio": "robotics & software | advisor @cline @icarus | early engineer @meta", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "safety-eval" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Tsunami-kun/awesome-humanoid-manipulation", "slug": "tsunami-kun-awesome-humanoid-manipulation", "url": "https://github.com/Tsunami-kun/awesome-humanoid-manipulation", "owner": "Tsunami-kun", "name": "awesome-humanoid-manipulation", "description": "A curated list of awesome papers and resources on humanoid manipulation, dexterous manipulation, bimanual dexterous manipulation, in-hand manipulation, and humanlike manipulation.", "readme": "Keywords : awesome humanoid manipulation, awesome dexterous manipulation, awesome bimanual manipulation, awesome dexterous hand, awesome humanoid robot, awesome robot hand manipulation, in-hand manipulation, dexterous grasping", "stars": 157, "stars_scraped": 156, "forks": 3, "watchers": 2, "language": null, "license": null, "gh_topics": [ "awesome", "awesome-list", "bimanual-manipulation", "dexterous-grasping", "dexterous-hand", "dexterous-manipulation", "humanlike-manipulation", "humanoid-manipulation", "humanoid-robot", "imitation-learning", "in-hand-manipulation", "manipulation", "reinforcement-learning", "robot", "robot-learning", "robot-manipulation", "sim-to-real", "teleoperation" ], "pushed_at": "2026-06-11", "created_at": "2024-10-19", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Tsunami", "owner_company": "Shanghai AI Laboratory", "owner_location": "Shanghai", "owner_url": "https://github.com/Tsunami-kun", "owner_repos": 25, "owner_followers": 14, "owner_bio": "\u300c\u6708\u591c\u3067\u306a\u3044\u3088\u3002\u9280\u6cb3\u3060\u304b\u3089\u5149\u308b\u3093\u3060\u3088\u3002\u300d", "affiliated_org": "Shanghai AI Lab", "link_sources": [], "papers": [], "topics": [ "dexterous-manipulation", "humanoids", "sim2real", "data-teleop" ], "score": 9, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "rise-policy/RISE", "slug": "rise-policy-rise", "url": "https://github.com/rise-policy/RISE", "owner": "rise-policy", "name": "RISE", "description": "[IROS 2024] \ud83d\udcc8 RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effective", "readme": "", "stars": 157, "stars_scraped": 157, "forks": 16, "watchers": 4, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "manipulation", "policy", "robotics" ], "pushed_at": "2025-11-29", "created_at": "2024-03-08", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "\ud83d\udcc8 RISE Policy", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/rise-policy", "owner_repos": 5, "owner_followers": 5, "owner_bio": "RISE: 3D Perception Makes Real-World Robot Imitation Simple and Effective", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "phi-monster/Galahad", "slug": "phi-monster-galahad", "url": "https://github.com/phi-monster/Galahad", "owner": "phi-monster", "name": "Galahad", "description": "Instruction blindness in vision-language-action policies: diagnosis and a low-rank data cure. Paper, model, deconfounded datasets, generator, and the measurement battery.", "readme": "The mechanism is a severed route, not missing knowledge. The pretrained backbone already resolves the named object in its language stream (activation patching localizes the binding to a single head; injecting the word direction flips the selected object 100% of the time), but the action head routes position and never reads that binding. Because the knowledge is present, the repair is a data recipe", "stars": 149, "stars_scraped": 149, "forks": 19, "watchers": 0, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "benchmark", "causal-confusion", "embodied-ai", "instruction-following", "interpretability", "language-grounding", "libero", "lora", "molmoact", "robot-learning", "robot-manipulation", "shortcut-learning", "vision-language-action", "vla" ], "pushed_at": "2026-07-25", "created_at": "2026-07-17", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "\u03a6(fight) Research", "owner_company": "", "owner_location": "Hong Kong", "owner_url": "https://github.com/phi-monster", "owner_repos": 3, "owner_followers": 27, "owner_bio": "Independent research collective for physical-world AI fighting. Pronounced \"fight.\"", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "NVlabs/alpamayo-recipes", "slug": "nvlabs-alpamayo-recipes", "url": "https://github.com/NVlabs/alpamayo-recipes", "owner": "NVlabs", "name": "alpamayo-recipes", "description": "Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning post-training, quantization, and deployment.", "readme": "NVIDIA Alpamayo is an open platform designed to accelerate the development of safe, transparent, and reasoning-based autonomous vehicles. It consists of vision-language-action (VLA) models, simulation frameworks, reinforcement learning infrastructure, and physical AI datasets and tools. The VLA models scale from the 10B-parameter Alpamayo 1 Nano and Alpamayo 1.5 Nano to the 34B-parameter Alpamayo ", "stars": 148, "stars_scraped": 142, "forks": 31, "watchers": 5, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "alpamayo", "autonomous-driving", "autonomous-vehicles", "fine-tuning", "nvidia", "physical-ai", "post-training", "quantization", "reasoning", "recipes", "reinforcement-learning", "robotics", "self-driving-car", "vision-language-action", "vla", "world-models" ], "pushed_at": "2026-08-05", "created_at": "2026-04-22", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "NVIDIA Research Projects", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/NVlabs", "owner_repos": 500, "owner_followers": 11191, "owner_bio": "", "affiliated_org": "NVIDIA", "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "rl-control" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Argo-Robot/foundation_models", "slug": "argo-robot-foundation-models", "url": "https://github.com/Argo-Robot/foundation_models", "owner": "Argo-Robot", "name": "foundation_models", "description": "Overview about state-of-art imitation learning techniques for robotic manipulation, enabling generalization across diverse tasks and environments.", "readme": "Whether you're an AI researcher, roboticist or just curious about the future of autonomous robots, this guide will provide a clear and engaging overview of the exciting innovations shaping the next generation of robotic manipulation.", "stars": 145, "stars_scraped": 145, "forks": 3, "watchers": 3, "language": null, "license": null, "gh_topics": [ "imitation-learning", "llms", "manipulation", "robotics", "transformers" ], "pushed_at": "2025-04-07", "created_at": "2025-04-05", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Argo", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Argo-Robot", "owner_repos": 8, "owner_followers": 38, "owner_bio": "AI Home Robot. Sharing our research and deep-dive tutorials on locomotion and manipulation!", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "imitation-diffusion" ], "score": 7, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "zhaozijie2022/LocoWheeledLegged", "slug": "zhaozijie2022-locowheeledlegged", "url": "https://github.com/zhaozijie2022/LocoWheeledLegged", "owner": "zhaozijie2022", "name": "LocoWheeledLegged", "description": "RL-based Legged-Wheeled Robot locomotion sim-to-real based on NVIDIA Isaac Lab", "readme": "", "stars": 143, "stars_scraped": 142, "forks": 11, "watchers": 1, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2026-07-09", "created_at": "2026-03-06", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Zijie Zhao", "owner_company": "Institute of Automation, Chinese Academy of Science", "owner_location": "95 Zhongguancun East Road, Beijing, China", "owner_url": "https://github.com/zhaozijie2022", "owner_repos": 7, "owner_followers": 42, "owner_bio": "Robot Learning, World Model, Reinforcement Learning", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real" ], "score": 14, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "ROBOTIS-GIT/cyclo_lab", "slug": "robotis-git-cyclo-lab", "url": "https://github.com/ROBOTIS-GIT/cyclo_lab", "owner": "ROBOTIS-GIT", "name": "cyclo_lab", "description": "This repository provides tutorials for reinforcement learning and imitation learning using ROBOTIS robots, and supports Sim2Real functionality for deploying the learned policies on real robots.", "readme": "Important", "stars": 142, "stars_scraped": 142, "forks": 25, "watchers": 1, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "imitation-learning", "isaaclab", "isaacsim", "reinforcement-learning", "robotics", "robotis", "robots", "sim2real" ], "pushed_at": "2026-08-26", "created_at": "2025-07-14", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "ROBOTIS", "owner_company": "", "owner_location": "#37, Magok Jungang 5-ro 1-gil, Gangseo-gu, Seoul, Korea", "owner_url": "https://github.com/ROBOTIS-GIT", "owner_repos": 153, "owner_followers": 1165, "owner_bio": "ROBOTIS Official GitHub", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real", "imitation-diffusion", "rl-control" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Toyota/yubi-hw", "slug": "toyota-yubi-hw", "url": "https://github.com/Toyota/yubi-hw", "owner": "Toyota", "name": "yubi-hw", "description": "YUBI - Yielding Universal Bidigital Interface - Open source hardware design for a finger-driven teleoperation glove and robot gripper, including CAD, BOM, and assembly instructions.", "readme": "\ud83c\udf10 Project page: yubi.airoa.io", "stars": 140, "stars_scraped": 130, "forks": 11, "watchers": 6, "language": null, "license": "CERN-OHL-W-2.0", "gh_topics": [], "pushed_at": "2026-08-20", "created_at": "2026-05-11", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Toyota", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Toyota", "owner_repos": 14, "owner_followers": 142, "owner_bio": "TOYOTA MOTOR CORPORATION", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "data-teleop", "hardware-codesign" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "OpenDriveLab/FreeTacMan", "slug": "opendrivelab-freetacman", "url": "https://github.com/OpenDriveLab/FreeTacMan", "owner": "OpenDriveLab", "name": "FreeTacMan", "description": "[ICRA 2026] FreeTacMan: Robot-free Visuo-Tactile Data Collection System for Contact-rich Manipulation", "readme": "", "stars": 139, "stars_scraped": 139, "forks": 11, "watchers": 4, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "robot-learning", "visuo-tactile" ], "pushed_at": "2026-02-02", "created_at": "2025-05-08", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "OpenDriveLab", "owner_company": "", "owner_location": "Hong Kong", "owner_url": "https://github.com/OpenDriveLab", "owner_repos": 54, "owner_followers": 2675, "owner_bio": "AI for Robotics and Autonomous Driving at The University of Hong Kong (HKU)", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "tactile", "data-teleop" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "MarkFzp/navigation-locomotion", "slug": "markfzp-navigation-locomotion", "url": "https://github.com/MarkFzp/navigation-locomotion", "owner": "MarkFzp", "name": "navigation-locomotion", "description": "[CVPR 2022] Codebase for \"Coupling Vision and Proprioception for Navigation of Legged Robots\"", "readme": "install by running install.sh", "stars": 134, "stars_scraped": 134, "forks": 10, "watchers": 6, "language": "C++", "license": "Apache-2.0", "gh_topics": [], "pushed_at": "2022-06-29", "created_at": "2021-12-04", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Zipeng Fu", "owner_company": "Stanford University", "owner_location": "Palo Alto, CA", "owner_url": "https://github.com/MarkFzp", "owner_repos": 16, "owner_followers": 1146, "owner_bio": "CS PhD at Stanford AI Lab. Working on Robotics and Machine Learning. ", "affiliated_org": "Stanford", "link_sources": [], "papers": [], "topics": [ "humanoids", "navigation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "NVlabs/handover-sim2real", "slug": "nvlabs-handover-sim2real", "url": "https://github.com/NVlabs/handover-sim2real", "owner": "NVlabs", "name": "handover-sim2real", "description": "Official code for CVPR'23 paper: Learning Human-to-Robot Handovers from Point Clouds", "readme": "Learning Human-to-Robot Handovers from Point Clouds Sammy Christen, Wei Yang, Claudia P\u00e9rez-D'Arpino, Otmar Hilliges, Dieter Fox, Yu-Wei Chao IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [ arXiv ] [ video ] [ project site ]", "stars": 130, "stars_scraped": 130, "forks": 22, "watchers": 5, "language": "Python", "license": "NOASSERTION", "gh_topics": [], "pushed_at": "2025-03-09", "created_at": "2023-10-26", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "NVIDIA Research Projects", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/NVlabs", "owner_repos": 500, "owner_followers": 11191, "owner_bio": "", "affiliated_org": "NVIDIA", "link_sources": [], "papers": [], "topics": [ "sim2real", "spatial-3d" ], "score": 6, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "x-zheng16/Awesome-Embodied-AI-Safety", "slug": "x-zheng16-awesome-embodied-ai-safety", "url": "https://github.com/x-zheng16/Awesome-Embodied-AI-Safety", "owner": "x-zheng16", "name": "Awesome-Embodied-AI-Safety", "description": "Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System", "readme": "[arXiv] | [Website] | [Latest Screened Papers]", "stars": 130, "stars_scraped": 129, "forks": 4, "watchers": 2, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "adversarial-attacks", "adversarial-robustness", "agent-safety", "ai-safety", "autonomous-driving", "awesome-list", "backdoor-attacks", "embodied-agents", "embodied-ai", "jailbreak", "large-language-models", "llm-safety", "prompt-injection", "red-teaming", "robotics", "survey", "trustworthy-ai", "vision-language-action", "world-action-model", "world-model" ], "pushed_at": "2026-08-26", "created_at": "2026-03-27", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Xiang Zheng", "owner_company": "City University of Hong Kong", "owner_location": "Hong Kong", "owner_url": "https://github.com/x-zheng16", "owner_repos": 34, "owner_followers": 33, "owner_bio": "Research Assistant Professor@CityUHK", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "safety-eval" ], "score": 7, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "lipengdong/hei-rebot-lift", "slug": "lipengdong-hei-rebot-lift", "url": "https://github.com/lipengdong/hei-rebot-lift", "owner": "lipengdong", "name": "hei-rebot-lift", "description": "HEI ReBot Lift is a LeRobot/ReBot-based dual-arm mobile robot with a lifting platform, omnidirectional chassis, three-view vision, and a VR + MuJoCo + Pinocchio IK teleoperation pipeline. It supports teleoperation, data recording, ACT/VLA training, and policy deployment.", "readme": "", "stars": 129, "stars_scraped": 124, "forks": 14, "watchers": 0, "language": "Python", "license": "Apache-2.0", "gh_topics": [], "pushed_at": "2026-08-01", "created_at": "2026-06-29", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "\u9ed1\u72d7\u6728", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/lipengdong", "owner_repos": 1, "owner_followers": 9, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "data-teleop" ], "score": 10, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "UT-Austin-RPL/TRILL", "slug": "ut-austin-rpl-trill", "url": "https://github.com/UT-Austin-RPL/TRILL", "owner": "UT-Austin-RPL", "name": "TRILL", "description": "Official codebase for TRILL (Teleoperation and Imitation Learning for Loco-manipulation)", "readme": "", "stars": 127, "stars_scraped": 127, "forks": 13, "watchers": 4, "language": "Python", "license": "MIT", "gh_topics": [ "deep-learning", "humanoid-robot", "imitation-learning", "robotics", "virtual-reality", "whole-body-control" ], "pushed_at": "2025-08-07", "created_at": "2023-07-23", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "UT Robot Perception and Learning Lab", "owner_company": "", "owner_location": "Austin, TX", "owner_url": "https://github.com/UT-Austin-RPL", "owner_repos": 40, "owner_followers": 205, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "imitation-diffusion", "data-teleop" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "wzzheng/SM4RT", "slug": "wzzheng-sm4rt", "url": "https://github.com/wzzheng/SM4RT", "owner": "wzzheng", "name": "SM4RT", "description": "Code for SM4RT: Learning Structured Motion Geometry for 4D Reconstruction", "readme": "Clone Repo", "stars": 125, "stars_scraped": 125, "forks": 4, "watchers": 4, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-19", "created_at": "", "archived": false, "paper_ids": [ "2607.22534" ], "owner_type": "User", "owner_display": "Wenzhao Zheng", "owner_company": "BAIR, UC Berkeley", "owner_location": "Berkeley", "owner_url": "https://github.com/wzzheng", "owner_repos": 32, "owner_followers": 569, "owner_bio": "", "affiliated_org": "UC Berkeley", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.22534", "slug": "sm4rt-learning-structured-motion-geometry-for-4d-reconstruction", "title": "SM4RT: Learning Structured Motion Geometry for 4D Reconstruction", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "graph-robots/graph-as-policy", "slug": "graph-robots-graph-as-policy", "url": "https://github.com/graph-robots/graph-as-policy", "owner": "graph-robots", "name": "graph-as-policy", "description": "gap \u2014 graph as policy: compile language instructions into typed, verified robot skill graphs and execute them on simulators or real robots", "readme": "", "stars": 121, "stars_scraped": 117, "forks": 7, "watchers": 3, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "agents", "llm", "manipulation", "robotics" ], "pushed_at": "2026-07-31", "created_at": "2026-06-09", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "graph-robots", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/graph-robots", "owner_repos": 5, "owner_followers": 13, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "jhu-lcsr/good_robot", "slug": "jhu-lcsr-good-robot", "url": "https://github.com/jhu-lcsr/good_robot", "owner": "jhu-lcsr", "name": "good_robot", "description": "\"Good Robot! Now Watch This!\": Repurposing Reinforcement Learning for Task-to-Task Transfer; and \u201cGood Robot!\u201d: Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer", "readme": "Paper , Poster", "stars": 121, "stars_scraped": 121, "forks": 29, "watchers": 12, "language": "Jupyter Notebook", "license": "BSD-2-Clause", "gh_topics": [ "computer-vision", "deep-learning", "deep-q-network", "deep-reinforcement-learning", "grasping", "learning-from-demonstration", "manipulation", "multi-step-dqn", "multi-step-learning", "reinforcement-learning", "robotic-manipulation", "robotics", "simulation", "task-to-task-transfer", "vrep-simulator", "zero-shot-learning" ], "pushed_at": "2022-03-25", "created_at": "2019-07-25", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "JHU Laboratory for Computational Sensing and Robotics", "owner_company": "", "owner_location": "Baltimore, MD, USA", "owner_url": "https://github.com/jhu-lcsr", "owner_repos": 67, "owner_followers": 54, "owner_bio": "Original code developed by members of the Johns Hopkins University Laboratory for Computational Sensing and Robotics", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "dexterous-manipulation", "sim2real", "rl-control" ], "score": 9, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "unitreerobotics/kinect_teleoperate", "slug": "unitreerobotics-kinect-teleoperate", "url": "https://github.com/unitreerobotics/kinect_teleoperate", "owner": "unitreerobotics", "name": "kinect_teleoperate", "description": "This repository implements teleoperation of the Unitree humanoid robot H1 / G1 using Azure Kinect DK camera.", "readme": "We tested our code on Ubuntu 20.04, other operating systems may be configured differently.", "stars": 120, "stars_scraped": 120, "forks": 29, "watchers": 2, "language": "C", "license": "BSD-3-Clause", "gh_topics": [], "pushed_at": "2024-08-13", "created_at": "2024-08-13", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Unitree Robotics", "owner_company": "", "owner_location": "Hangzhou China", "owner_url": "https://github.com/unitreerobotics", "owner_repos": 53, "owner_followers": 6772, "owner_bio": "High performance civilian robot manufacturer. Please everyone be sure to use the robot in a Friendly and Safe manner.", "affiliated_org": "Unitree", "link_sources": [], "papers": [], "topics": [ "humanoids", "data-teleop" ], "score": 6, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "OpenDriveLab/MPI", "slug": "opendrivelab-mpi", "url": "https://github.com/OpenDriveLab/MPI", "owner": "OpenDriveLab", "name": "MPI", "description": "[RSS 2024] Learning Manipulation by Predicting Interaction", "readme": "", "stars": 118, "stars_scraped": 118, "forks": 2, "watchers": 4, "language": null, "license": null, "gh_topics": [ "policy-learning", "pre-training", "robot-manipulation" ], "pushed_at": "2025-07-02", "created_at": "", "archived": false, "paper_ids": [ "2406.00439" ], "owner_type": "Organization", "owner_display": "OpenDriveLab", "owner_company": "", "owner_location": "Hong Kong", "owner_url": "https://github.com/OpenDriveLab", "owner_repos": 54, "owner_followers": 2675, "owner_bio": "AI for Robotics and Autonomous Driving at The University of Hong Kong (HKU)", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2406.00439", "slug": "learning-manipulation-by-predicting-interaction", "title": "Learning Manipulation by Predicting Interaction", "featured": false } ], "topics": [ "foundation-pretraining" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "ShengqianChen/DreamWaQ_Go2W", "slug": "shengqianchen-dreamwaq-go2w", "url": "https://github.com/ShengqianChen/DreamWaQ_Go2W", "owner": "ShengqianChen", "name": "DreamWaQ_Go2W", "description": "A Go2W legged-wheel robot locomotion reinforcement learning project based on NVIDIA Isaac Gym.", "readme": "", "stars": 115, "stars_scraped": 115, "forks": 9, "watchers": 2, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2026-05-12", "created_at": "2025-05-26", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Shengqian Chen", "owner_company": "Institute of Automation, Chinese Academy of Science", "owner_location": "95 Zhongguancun East Road, Beijing, China", "owner_url": "https://github.com/ShengqianChen", "owner_repos": 2, "owner_followers": 17, "owner_bio": "\u77e5\u8005\u884c\u4e4b\u4f7f \u884c\u8005\u77e5\u4e4b\u6210", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "rl-control" ], "score": 10, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "isaac-sim2real/sage", "slug": "isaac-sim2real-sage", "url": "https://github.com/isaac-sim2real/sage", "owner": "isaac-sim2real", "name": "sage", "description": "Framework for measuring sim-to-real gaps in robot joint motions. Supports different humanoids with physics simulation, real hardware data collection, and statistical analysis.", "readme": "SAGE combines:", "stars": 113, "stars_scraped": 112, "forks": 16, "watchers": 3, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "isaac-sim", "joint-motion", "robotics", "sim-to-real" ], "pushed_at": "2026-04-28", "created_at": "2025-09-05", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "isaac-sim2real", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/isaac-sim2real", "owner_repos": 1, "owner_followers": 9, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real", "data-teleop" ], "score": 11, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "facebookresearch/project_superdex", "slug": "facebookresearch-project-superdex", "url": "https://github.com/facebookresearch/project_superdex", "owner": "facebookresearch", "name": "project_superdex", "description": "SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and additional capabilities planned for future releases.", "readme": "SuperDex brings together a purpose-built physics engine, robotics authoring tools, and a scalable reinforcement learning interface in a unified simulation platform, with VR-based teleoperation and additional capabilities planned for future releases.", "stars": 108, "stars_scraped": 272, "forks": 9, "watchers": 6, "language": "C++", "license": "Apache-2.0", "gh_topics": [], "pushed_at": "2026-08-26", "created_at": "2026-08-20", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Meta Research", "owner_company": "", "owner_location": "Menlo Park, California", "owner_url": "https://github.com/facebookresearch", "owner_repos": 1436, "owner_followers": 37143, "owner_bio": "", "affiliated_org": "Meta FAIR", "link_sources": [], "papers": [], "topics": [ "rl-control", "data-teleop" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "eanswer/TactileSimulation", "slug": "eanswer-tactilesimulation", "url": "https://github.com/eanswer/TactileSimulation", "owner": "eanswer", "name": "TactileSimulation", "description": "[CoRL 2022] Efficient Tactile Simulation with Differentiability for Robotic Manipulation", "readme": "", "stars": 105, "stars_scraped": 105, "forks": 6, "watchers": 2, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2024-01-15", "created_at": "2022-12-31", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Jie Xu", "owner_company": "NVIDIA", "owner_location": "Seattle, Washington", "owner_url": "https://github.com/eanswer", "owner_repos": 15, "owner_followers": 198, "owner_bio": "Robotics Research Scientist at NVIDIA. Previously Ph.D. from MIT CSAIL.\r\n \r\n", "affiliated_org": "NVIDIA", "link_sources": [], "papers": [], "topics": [ "tactile" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "trzy/robot-arm", "slug": "trzy-robot-arm", "url": "https://github.com/trzy/robot-arm", "owner": "trzy", "name": "robot-arm", "description": "Imitation learning with iPhone based teleoperation of a low-cost robot arm.", "readme": "The low-cost 4dof arm.", "stars": 105, "stars_scraped": 105, "forks": 8, "watchers": 3, "language": "Python", "license": null, "gh_topics": [ "ai", "arkit", "imitation-learning", "ios", "pytorch", "robotics", "teleoperation" ], "pushed_at": "2024-09-16", "created_at": "2024-04-15", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Bart Trzynadlowski", "owner_company": "", "owner_location": "New York, NY", "owner_url": "https://github.com/trzy", "owner_repos": 49, "owner_followers": 295, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "imitation-diffusion", "data-teleop" ], "score": 8, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "carlosferrazza/tactile_envs", "slug": "carlosferrazza-tactile-envs", "url": "https://github.com/carlosferrazza/tactile_envs", "owner": "carlosferrazza", "name": "tactile_envs", "description": "Collection of MuJoCo robotics environments equipped with both vision and tactile sensing", "readme": "Current available environments:", "stars": 102, "stars_scraped": 102, "forks": 6, "watchers": 3, "language": "Python", "license": "NOASSERTION", "gh_topics": [], "pushed_at": "2024-07-08", "created_at": "2024-06-27", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Carlo Sferrazza", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/carlosferrazza", "owner_repos": 12, "owner_followers": 73, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "tactile" ], "score": 7, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "sun254667/awesome-touch", "slug": "sun254667-awesome-touch", "url": "https://github.com/sun254667/awesome-touch", "owner": "sun254667", "name": "awesome-touch", "description": "A curated, learning-friendly list of tactile sensing research resources for robotic manipulation: papers, datasets, benchmarks, simulation platforms, and frameworks, covering the integration of touch with Vision-Language-Action (VLA) models and World Models for contact-rich manipulation", "readme": "A curated, learning-friendly list of tactile sensing research resources for robotic manipulation: papers, datasets, benchmarks, simulation platforms, and frameworks, covering the integration of touch with Vision-Language-Action (VLA) models and World Models for contact-rich manipulation. Time range: 2025.01 \u2013 2026.07.", "stars": 97, "stars_scraped": 98, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [ "awesome-list", "tactile", "tactile-sensing", "tactile-sensor", "touch", "vla", "world-model" ], "pushed_at": "2026-08-02", "created_at": "2026-08-02", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "yuanliang sun", "owner_company": "DataArc", "owner_location": "", "owner_url": "https://github.com/sun254667", "owner_repos": 4, "owner_followers": 2, "owner_bio": "sun254667307@gmail.com", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "vla", "tactile" ], "score": 11, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "jrobine/twm", "slug": "jrobine-twm", "url": "https://github.com/jrobine/twm", "owner": "jrobine", "name": "twm", "description": "Transformer-based World Models", "readme": "Install packages from requirements.txt . Also make sure you have installed the Atari environments correctly. For more information, see: https://github.com/openai/gym/releases/tag/v0.21.0", "stars": 91, "stars_scraped": 91, "forks": 10, "watchers": 3, "language": null, "license": null, "gh_topics": [ "artificial-intelligence", "atari", "deep-learning", "iclr2023", "machine-learning", "reinforcement-learning", "research", "world-models" ], "pushed_at": "2023-04-04", "created_at": "", "archived": false, "paper_ids": [ "2303.07109" ], "owner_type": "User", "owner_display": "Jan Robine", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/jrobine", "owner_repos": 6, "owner_followers": 9, "owner_bio": "PhD student interested in Reinforcement Learning, Deep Learning and Representation Learning.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2303.07109", "slug": "transformer-based-world-models-are-happy-with-100k-interactions", "title": "Transformer-based World Models Are Happy With 100k Interactions", "featured": false } ], "topics": [ "world-models" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "yxyang/fast_and_efficient", "slug": "yxyang-fast-and-efficient", "url": "https://github.com/yxyang/fast_and_efficient", "owner": "yxyang", "name": "fast_and_efficient", "description": "", "readme": "change world argument to be one of [plane, slope, stair, uneven] for different worlds. The current MPC controller has been tuned for all four worlds.", "stars": 91, "stars_scraped": 91, "forks": 16, "watchers": 3, "language": null, "license": null, "gh_topics": [], "pushed_at": "2023-03-28", "created_at": "", "archived": false, "paper_ids": [ "2104.04644" ], "owner_type": "User", "owner_display": "Yuxiang Yang", "owner_company": "Google Deepmind", "owner_location": "", "owner_url": "https://github.com/yxyang", "owner_repos": 28, "owner_followers": 122, "owner_bio": "Research Scientist @ Google Deepmind, Former PhD student in Robotics at University of Washington", "affiliated_org": "Google DeepMind", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2104.04644", "slug": "fast-and-efficient-locomotion-via-learned-gait-transitions", "title": "Fast and Efficient Locomotion via Learned Gait Transitions", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "alibaba-damo-academy/RynnWorld-4D", "slug": "alibaba-damo-academy-rynnworld-4d", "url": "https://github.com/alibaba-damo-academy/RynnWorld-4D", "owner": "alibaba-damo-academy", "name": "RynnWorld-4D", "description": "RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation", "readme": "", "stars": 86, "stars_scraped": 85, "forks": 7, "watchers": 1, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-07-16", "created_at": "", "archived": false, "paper_ids": [ "2607.06559" ], "owner_type": "Organization", "owner_display": "Alibaba DAMO Academy", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/alibaba-damo-academy", "owner_repos": 82, "owner_followers": 947, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.06559", "slug": "rynnworld-4d-4d-embodied-world-models-for-robotic-manipulation", "title": "RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation", "featured": false } ], "topics": [ "world-models" ], "score": 5, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "robotology/blender-robotics-utils", "slug": "robotology-blender-robotics-utils", "url": "https://github.com/robotology/blender-robotics-utils", "owner": "robotology", "name": "blender-robotics-utils", "description": "Set of utilities for exporting/controlling your robot in Blender", "readme": "This repository is maintained by:", "stars": 83, "stars_scraped": 83, "forks": 11, "watchers": 8, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "blender", "humanoid-robot", "idyntree", "python", "robotics", "robots", "urdf", "urdf-models", "urdf-parser" ], "pushed_at": "2024-12-04", "created_at": "2021-07-28", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Robotology", "owner_company": "", "owner_location": "Italy", "owner_url": "https://github.com/robotology", "owner_repos": 153, "owner_followers": 335, "owner_bio": "Group software repositories of the iCub eco-system (but code developed is not necessarily iCub specific!).", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "Lax3n/HumanTyping", "slug": "lax3n-humantyping", "url": "https://github.com/Lax3n/HumanTyping", "owner": "Lax3n", "name": "HumanTyping", "description": "The most realistic keyboard typing simulator based on Markov Chains. Models authentic human behavior (errors, corrections, fatigue, speed variations) for Playwright and Selenium automation.", "readme": "HumanTyping models authentic human typing behavior with unprecedented accuracy, making automated typing indistinguishable from real users.", "stars": 78, "stars_scraped": 78, "forks": 12, "watchers": 0, "language": "Python", "license": "MIT", "gh_topics": [ "anti-detection", "automation", "bot-detection", "human-behavior", "human-computer-interaction", "humanoid-robot", "playwright", "playwright-automation", "playwright-python", "stochastic-processes", "typing-simulator" ], "pushed_at": "2026-07-05", "created_at": "2025-11-22", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Alexandre", "owner_company": "Universit\u00e9 C\u00f4te d'Azur", "owner_location": "Nice", "owner_url": "https://github.com/Lax3n", "owner_repos": 14, "owner_followers": 12, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "sim2real" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "purdue-tracelab/PACE-ICRA2026", "slug": "purdue-tracelab-pace-icra2026", "url": "https://github.com/purdue-tracelab/PACE-ICRA2026", "owner": "purdue-tracelab", "name": "PACE-ICRA2026", "description": "[ICRA2026] \"PACE: Physics Augmentation for Coordinated End-to-end Reinforcement Learning toward Versatile Humanoid Table Tennis\"", "readme": "Goal: Train a single, end-to-end RL policy that directly maps ball position observations + robot proprioception to whole-body joint commands so a humanoid can both move (footwork) and strike (paddle control) fast enough for table tennis.", "stars": 78, "stars_scraped": 77, "forks": 10, "watchers": 2, "language": "Python", "license": "MIT", "gh_topics": [ "athletic-ai", "humanoid-robot", "humanoid-table-tennis", "reinforcement-learning", "whole-body-control" ], "pushed_at": "2026-08-24", "created_at": "2026-02-13", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "purdue-tracelab", "owner_company": "", "owner_location": "United States of America", "owner_url": "https://github.com/purdue-tracelab", "owner_repos": 8, "owner_followers": 20, "owner_bio": "The Terrain Robotics Advanced Control and Experimentation (TRACE) Lab", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "rl-control" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "AravinthPanch/gesture-recognition-for-human-robot-interaction", "slug": "aravinthpanch-gesture-recognition-for-human-robot-interaction", "url": "https://github.com/AravinthPanch/gesture-recognition-for-human-robot-interaction", "owner": "AravinthPanch", "name": "gesture-recognition-for-human-robot-interaction", "description": "Gesture Recognition For Human-Robot Interaction with modelling, training, analysing and recognising gestures based on computer vision and machine learning techniques. This work was done at Distributed Artificial Intelligence Lab (DAI Labor), Berlin.", "readme": "In order to recognize gestures, we propose to learn and classify hand gestures with the help of Adaptive Naive Bayes Classifier using Gesture Recognition Toolkit. Furthermore, we aim to build a dashboard that can visualize the interaction between all essential parts of the system. Finally, we attempt to integrate all these functionalities into a system that interacts with a humanoid robot NAO.", "stars": 76, "stars_scraped": 76, "forks": 34, "watchers": 11, "language": "C++", "license": "Apache-2.0", "gh_topics": [ "adaptive-naive-bayes-classifier", "asus-xtion-pro-live", "c-plus-plus", "depth-camera", "gesture-recognition", "gesture-recognition-toolkit", "hand-gestures", "human-robot-interaction", "humanoid-robot", "machine-learning", "nao", "openni", "skeletal-points-tracking" ], "pushed_at": "2019-10-12", "created_at": "2014-12-09", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Aravinth Panch", "owner_company": "araCreate GmbH", "owner_location": "Berlin", "owner_url": "https://github.com/AravinthPanch", "owner_repos": 36, "owner_followers": 77, "owner_bio": "Social & Tech Entrepreneur", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "hri" ], "score": 4, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "jessicayin/osmo_tactile_glove", "slug": "jessicayin-osmo-tactile-glove", "url": "https://github.com/jessicayin/osmo_tactile_glove", "owner": "jessicayin", "name": "osmo_tactile_glove", "description": "Open source tactile glove for robotics research", "readme": "Project website: jessicayin.github.io/osmo_tactile_glove", "stars": 74, "stars_scraped": 73, "forks": 17, "watchers": 3, "language": "C", "license": null, "gh_topics": [], "pushed_at": "2026-05-01", "created_at": "2025-10-24", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Jessica Yin", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/jessicayin", "owner_repos": 5, "owner_followers": 7, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "tactile" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "DAInamite/programming-humanoid-robot-in-python", "slug": "dainamite-programming-humanoid-robot-in-python", "url": "https://github.com/DAInamite/programming-humanoid-robot-in-python", "owner": "DAInamite", "name": "programming-humanoid-robot-in-python", "description": "Programming Humanoid Robot In Python", "readme": "The demo showed in lecture are included in this repo as well, please check files (mostly *.ipynb) in subfolders.", "stars": 73, "stars_scraped": 73, "forks": 299, "watchers": 9, "language": "Jupyter Notebook", "license": "GPL-2.0", "gh_topics": [ "exercise", "humanoid-robot", "python", "robocup" ], "pushed_at": "2024-10-21", "created_at": "2014-10-20", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "DAInamite", "owner_company": "", "owner_location": "Berlin", "owner_url": "https://github.com/DAInamite", "owner_repos": 28, "owner_followers": 3, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "Frank-ZY-Dou/Dynamics-Modeling", "slug": "frank-zy-dou-dynamics-modeling", "url": "https://github.com/Frank-ZY-Dou/Dynamics-Modeling", "owner": "Frank-ZY-Dou", "name": "Dynamics-Modeling", "description": "", "readme": "", "stars": 72, "stars_scraped": 72, "forks": 2, "watchers": 2, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-07-22", "created_at": "", "archived": false, "paper_ids": [ "2607.11734" ], "owner_type": "User", "owner_display": "Frank Zhiyang Dou", "owner_company": "PhD at MIT, MPhil at HKU, Visiting Student at UPenn", "owner_location": "Cambridge", "owner_url": "https://github.com/Frank-ZY-Dou", "owner_repos": 21, "owner_followers": 234, "owner_bio": "PhD @ MIT. \r\nVisiting @ UPenn.\r\nMPhil @ HKU.\r\n \r\nResearch interests: Simulation, Robotics, Character Animation, Geometry Processing, Graphics.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.11734", "slug": "neuralactuator-neural-actuation-modeling-for-robot-dynamics-and-extern", "title": "NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "irmakguzey/tactile-dexterity", "slug": "irmakguzey-tactile-dexterity", "url": "https://github.com/irmakguzey/tactile-dexterity", "owner": "irmakguzey", "name": "tactile-dexterity", "description": "Official implementation of Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Play.", "readme": "", "stars": 70, "stars_scraped": 70, "forks": 9, "watchers": 1, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2024-02-09", "created_at": "2023-03-13", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Irmak Guzey", "owner_company": "NYU, META", "owner_location": "", "owner_url": "https://github.com/irmakguzey", "owner_repos": 32, "owner_followers": 56, "owner_bio": "PhD student at NYU. Working on robot learning for dexterous manipulation.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "dexterous-manipulation", "tactile", "foundation-pretraining" ], "score": 9, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "Shuijing725/CrowdNav_Sim2Real_Turtlebot", "slug": "shuijing725-crowdnav-sim2real-turtlebot", "url": "https://github.com/Shuijing725/CrowdNav_Sim2Real_Turtlebot", "owner": "Shuijing725", "name": "CrowdNav_Sim2Real_Turtlebot", "description": "[ICRA 2023] Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph -- Sim2real code on Turtlebot2i", "readme": "This repo only serves as a reference point for the sim2real transfer of crowd navigation. Since there are lots of uncertainties in real-world experiments that may affect performance, we cannot guarantee that our result is reproducible in your case.", "stars": 67, "stars_scraped": 67, "forks": 7, "watchers": 1, "language": "Python", "license": null, "gh_topics": [ "collision-avoidance", "crowd-navigation", "human-robot-interaction", "machine-learning", "reinforcement-learning", "ros", "sim2real", "turtlebot2" ], "pushed_at": "2024-12-13", "created_at": "2023-04-20", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Shuijing Liu", "owner_company": "", "owner_location": "Urbana, IL, USA", "owner_url": "https://github.com/Shuijing725", "owner_repos": 20, "owner_followers": 140, "owner_bio": "Robot learning + Human robot interaction. UT Austin postdoc, UIUC PhD.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real", "navigation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "bigai-ai/PP-Tac", "slug": "bigai-ai-pp-tac", "url": "https://github.com/bigai-ai/PP-Tac", "owner": "bigai-ai", "name": "PP-Tac", "description": "This is the implementation of PP-Tac: Paper Picking Using Tactile Feedback in Dexterous Robotic Hands", "readme": "[Project page] [Paper] [Video Tutorial_Youtube] [Video Tutorial_Bilibili]", "stars": 66, "stars_scraped": 66, "forks": 7, "watchers": 8, "language": "Python", "license": null, "gh_topics": [], "pushed_at": "2026-07-10", "created_at": "2025-05-07", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Beijing Institute for General Artificial Intelligence", "owner_company": "", "owner_location": "China", "owner_url": "https://github.com/bigai-ai", "owner_repos": 34, "owner_followers": 145, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "dexterous-manipulation", "tactile" ], "score": 8, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "open-rdc/ROS2_Walking_Pattern_Generator", "slug": "open-rdc-ros2-walking-pattern-generator", "url": "https://github.com/open-rdc/ROS2_Walking_Pattern_Generator", "owner": "open-rdc", "name": "ROS2_Walking_Pattern_Generator", "description": "Walking Pattern Generator (= Walking Controller) using ROS2 for Humanoid Robots", "readme": "It is compatible with the following OS:", "stars": 63, "stars_scraped": 63, "forks": 7, "watchers": 6, "language": "C++", "license": "Apache-2.0", "gh_topics": [ "humanoid", "humanoid-control", "humanoid-robot", "humanoid-walking", "robotics", "ros", "ros2" ], "pushed_at": "2025-06-24", "created_at": "2022-10-07", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "open-rdc", "owner_company": "", "owner_location": "2-17-1, Tsudanuma, Narashino, Chiba, JAPAN", "owner_url": "https://github.com/open-rdc", "owner_repos": 152, "owner_followers": 45, "owner_bio": "Robot Design and Control Lab @ CIT", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "GTLIDAR/DeformableObjectsGrasping", "slug": "gtlidar-deformableobjectsgrasping", "url": "https://github.com/GTLIDAR/DeformableObjectsGrasping", "owner": "GTLIDAR", "name": "DeformableObjectsGrasping", "description": "", "readme": "Grasping Framework Original work done as part of our paper. we propose a Transformer-based robotic grasping framework for rigid grippers that leverage tactile and visual information for safe object grasping. Specificaylly, our framework can predict the grasping outcome given a grasping force threshold and to estimate the force threshold for safe grasping through inference.", "stars": 60, "stars_scraped": 60, "forks": 3, "watchers": 2, "language": null, "license": null, "gh_topics": [], "pushed_at": "2023-12-07", "created_at": "", "archived": false, "paper_ids": [ "2112.06374" ], "owner_type": "Organization", "owner_display": "Laboratory for Intelligent Decision and Autonomous Robots", "owner_company": "", "owner_location": "Atlanta", "owner_url": "https://github.com/GTLIDAR", "owner_repos": 44, "owner_followers": 59, "owner_bio": "", "affiliated_org": null, "link_sources": [ "paper-fulltext" ], "papers": [ { "id": "2112.06374", "slug": "learning-generalizable-vision-tactile-robotic-grasping-strategy-for-de", "title": "Learning Generalizable Vision-Tactile Robotic Grasping Strategy for Deformable Objects via Transformer", "featured": true } ], "topics": [ "dexterous-manipulation", "tactile" ], "score": 6, "from_paper": false, "link_strength": "mentioned", "stale": false }, { "full_name": "linchangyi1/LocoTouch", "slug": "linchangyi1-locotouch", "url": "https://github.com/linchangyi1/LocoTouch", "owner": "linchangyi1", "name": "LocoTouch", "description": "Perceptive Learning for Legged Robots in IsaacLab. | LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sensing (CoRL'25)", "readme": "Please note that the official implementation of LocoTouch is built on IsaacSim 4.5 and IsaacLab 1.40. To reproduce LocoTouch with Ubuntu 20.04, please refer to the ubuntu-20 branch.", "stars": 60, "stars_scraped": 60, "forks": 5, "watchers": 3, "language": "Python", "license": "MIT", "gh_topics": [], "pushed_at": "2026-05-15", "created_at": "2025-05-16", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Changyi Lin", "owner_company": "Carnegie Mellon University", "owner_location": "Pittsburgh", "owner_url": "https://github.com/linchangyi1", "owner_repos": 9, "owner_followers": 135, "owner_bio": "PhD Student @ CMU Safe AI Lab", "affiliated_org": "CMU", "link_sources": [], "papers": [], "topics": [ "humanoids", "tactile" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "AMAP-ML/DreamX-Phi", "slug": "amap-ml-dreamx-phi", "url": "https://github.com/AMAP-ML/DreamX-Phi", "owner": "AMAP-ML", "name": "DreamX-Phi", "description": "DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation", "readme": "DreamX-Phi is a geometry-aware video world model built on Wan2.2-TI2V-5B. Given an initial observation and a prescribed robot action sequence, it predicts the corresponding future video while preserving robot motion, scene geometry, and the state of the manipulated object.", "stars": 61, "stars_scraped": 59, "forks": 2, "watchers": 2, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-14", "created_at": "", "archived": false, "paper_ids": [ "2608.13489" ], "owner_type": "Organization", "owner_display": "DreamX", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/AMAP-ML", "owner_repos": 46, "owner_followers": 337, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.13489", "slug": "dreamx-phi-1-0-action-conditioned-video-world-model-for-robotic-manipu", "title": "DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation", "featured": false } ], "topics": [ "world-models" ], "score": 5, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "MrSecant/OmniVTA", "slug": "mrsecant-omnivta", "url": "https://github.com/MrSecant/OmniVTA", "owner": "MrSecant", "name": "OmniVTA", "description": "OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation ", "readme": "", "stars": 59, "stars_scraped": 59, "forks": 1, "watchers": 8, "language": null, "license": "MIT", "gh_topics": [], "pushed_at": "2026-08-10", "created_at": "2026-03-01", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Yuhang Zheng", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/MrSecant", "owner_repos": 9, "owner_followers": 22, "owner_bio": "Member of AnySyn3D", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "world-models", "tactile" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "openai/ppo-ewma", "slug": "openai-ppo-ewma", "url": "https://github.com/openai/ppo-ewma", "owner": "openai", "name": "ppo-ewma", "description": "Code for the paper \"Batch size invariance for policy optimization\"", "readme": "Supported platforms: MacOS and Ubuntu, Python 3.7", "stars": 59, "stars_scraped": 59, "forks": 14, "watchers": 1, "language": null, "license": null, "gh_topics": [], "pushed_at": "2023-04-02", "created_at": "", "archived": true, "paper_ids": [ "2110.00641" ], "owner_type": "Organization", "owner_display": "OpenAI", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/openai", "owner_repos": 268, "owner_followers": 131070, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2110.00641", "slug": "batch-size-invariance-for-policy-optimization", "title": "Batch size-invariance for policy optimization", "featured": false } ], "topics": [ "rl-control" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "nvidia-isaac/nvblox_mindmap", "slug": "nvidia-isaac-nvblox-mindmap", "url": "https://github.com/nvidia-isaac/nvblox_mindmap", "owner": "nvidia-isaac", "name": "nvblox_mindmap", "description": "mindmap: Spatial Memory in Deep Feature Maps for 3D Action Policies", "readme": "Our mindmap paper demonstrates that mindmap effectively solves manipulation tasks where state-of-the-art approaches without memory mechanisms struggle. Through extensive simulation experiments, we show significant improvements in task success rates for scenarios requiring spatial memory.", "stars": 58, "stars_scraped": 56, "forks": 2, "watchers": 1, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "3d-reconstruction", "feature-mapping", "humanoid-robot", "robotics", "spatial-memory", "vision-language-action-model" ], "pushed_at": "2025-10-16", "created_at": "2025-10-07", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "NVIDIA Isaac", "owner_company": "", "owner_location": "United States of America", "owner_url": "https://github.com/nvidia-isaac", "owner_repos": 23, "owner_followers": 464, "owner_bio": "High-performance building blocks and tools for robotics", "affiliated_org": "NVIDIA", "link_sources": [], "papers": [], "topics": [ "vla", "humanoids" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "TingdeLiu/tingdeliu.github.io", "slug": "tingdeliu-tingdeliu-github-io", "url": "https://github.com/TingdeLiu/tingdeliu.github.io", "owner": "TingdeLiu", "name": "tingdeliu.github.io", "description": "My Personal Blog (Robotics)", "readme": "\u8bbf\u95ee\u7f51\u7ad9 \u00b7 \u7814\u7a76\u7efc\u8ff0 \u00b7 \u6280\u672f\u535a\u5ba2 \u00b7 \u5f00\u6e90\u9879\u76ee \u00b7 \u5173\u4e8e\u4f5c\u8005", "stars": 57, "stars_scraped": 50, "forks": 1, "watchers": 1, "language": "SCSS", "license": null, "gh_topics": [ "ai-agent", "chinese", "embodied-ai", "multimodal-learning", "research-notes", "robot-navigation", "robotics", "vision-language-action", "visual-language-navigation" ], "pushed_at": "2026-08-26", "created_at": "2026-01-04", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Tingde Liu", "owner_company": "Leibniz Universit\u00e4t", "owner_location": "Hannover", "owner_url": "https://github.com/TingdeLiu", "owner_repos": 17, "owner_followers": 24, "owner_bio": "Embodied AI Engineer @ Beijing | Robotics MS from LUH", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "navigation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "ammar-n-abbas/sim2real-ur-gym-gazebo", "slug": "ammar-n-abbas-sim2real-ur-gym-gazebo", "url": "https://github.com/ammar-n-abbas/sim2real-ur-gym-gazebo", "owner": "ammar-n-abbas", "name": "sim2real-ur-gym-gazebo", "description": "Universal Robot Environment for OpenAI Gymnasium and ROS Gazebo Interface", "readme": "Sim2Real zero-shot transfer of gasping policy using safe-DRL", "stars": 54, "stars_scraped": 54, "forks": 6, "watchers": 1, "language": "C++", "license": "MIT", "gh_topics": [], "pushed_at": "2025-04-12", "created_at": "2023-10-11", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Ammar N. Abbas", "owner_company": "Technological University Dublin", "owner_location": "Ireland", "owner_url": "https://github.com/ammar-n-abbas", "owner_repos": 22, "owner_followers": 25, "owner_bio": "I am an Erasmus scholar with a Master's in Mechatronics and a Ph.D. in Deep Reinforcement Learning under the Marie Curie Fellowship program. ", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "sim2real" ], "score": 9, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "tsinghua-rll/Visual-Tactile_Dataset", "slug": "tsinghua-rll-visual-tactile-dataset", "url": "https://github.com/tsinghua-rll/Visual-Tactile_Dataset", "owner": "tsinghua-rll", "name": "Visual-Tactile_Dataset", "description": "A novel visual-tactile dataset for robotic manipulation", "readme": "It is recommanded to use numpy function loadtxt to load the .txt files, opencv function imread to load .jpg files, and opencv function VideoCapture to open .mp4 files. Here is an example.", "stars": 53, "stars_scraped": 53, "forks": 15, "watchers": 2, "language": null, "license": "NOASSERTION", "gh_topics": [], "pushed_at": "2019-08-25", "created_at": "2018-08-14", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Tsinghua Robot Learning Lab", "owner_company": "", "owner_location": "Beijing, China", "owner_url": "https://github.com/tsinghua-rll", "owner_repos": 20, "owner_followers": 10, "owner_bio": "", "affiliated_org": "Tsinghua", "link_sources": [], "papers": [], "topics": [ "tactile" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "ekorudiawan/ZMP-Preview-Control-WPG", "slug": "ekorudiawan-zmp-preview-control-wpg", "url": "https://github.com/ekorudiawan/ZMP-Preview-Control-WPG", "owner": "ekorudiawan", "name": "ZMP-Preview-Control-WPG", "description": "ZMP Preview Control Walking Pattern Generation for Biped Humanoid Robot", "readme": "Zero Moment Point (ZMP) Preview Control for biped walking pattern generation, ported from MATLAB to pure Python with no proprietary dependencies.", "stars": 51, "stars_scraped": 51, "forks": 8, "watchers": 1, "language": "Python", "license": "MIT", "gh_topics": [ "humanoid-robot", "humanoid-robots", "humanoid-walking", "walking-controller", "walking-pattern-generation" ], "pushed_at": "2026-06-26", "created_at": "2019-09-06", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Eko Rudiawan Jamzuri", "owner_company": "Politeknik Negeri Batam", "owner_location": "Batam, Indonesia", "owner_url": "https://github.com/ekorudiawan", "owner_repos": 155, "owner_followers": 107, "owner_bio": "Addicted to Code & Coffee ", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "GalacTechNyc/unitree-g1-autonomous", "slug": "galactechnyc-unitree-g1-autonomous", "url": "https://github.com/GalacTechNyc/unitree-g1-autonomous", "owner": "GalacTechNyc", "name": "unitree-g1-autonomous", "description": "\ud83e\udd16 Fully autonomous navigation system for Unitree G1 humanoid robot using AI-powered visual analysis with Google Gemini API", "readme": "", "stars": 50, "stars_scraped": 50, "forks": 7, "watchers": 1, "language": "Python", "license": "NOASSERTION", "gh_topics": [ "ai", "autonomous-navigation", "computer-vision", "gemini-api", "humanoid-robot", "python", "robotics", "unitree" ], "pushed_at": "2025-07-28", "created_at": "2025-07-28", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "GalacTechNyc", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/GalacTechNyc", "owner_repos": 13, "owner_followers": 0, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "navigation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "incognite-lab/Pepper-Controller", "slug": "incognite-lab-pepper-controller", "url": "https://github.com/incognite-lab/Pepper-Controller", "owner": "incognite-lab", "name": "Pepper-Controller", "description": "Python controller for Pepper humanoid robot. It allows to write apps in Python. There are examples of simple applications for Pepper. We develop GUI to operate the robot and run custom apps ", "readme": "Python 2.7 (or Python 3.5.6 with limited functionality)", "stars": 49, "stars_scraped": 50, "forks": 17, "watchers": 1, "language": "Python", "license": null, "gh_topics": [ "gui", "human-robot-interaction", "humanoid-robot", "language", "navigation", "pepper", "pepper-robot", "python", "social-interactions", "vision" ], "pushed_at": "2026-02-23", "created_at": "2020-12-14", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "Incognite", "owner_company": "", "owner_location": "Prague", "owner_url": "https://github.com/incognite-lab", "owner_repos": 6, "owner_followers": 4, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids", "navigation" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "simonepri/roboprime", "slug": "simonepri-roboprime", "url": "https://github.com/simonepri/roboprime", "owner": "simonepri", "name": "roboprime", "description": "\ud83e\udd16 Full featured 21 DOF 3D Printed Humanoid Robot based on ATmega328P chip", "readme": "The project has been featured here:", "stars": 49, "stars_scraped": 49, "forks": 9, "watchers": 4, "language": "Arduino", "license": "GPL-3.0", "gh_topics": [ "3d-printing", "arduino", "atmega328p", "electronics", "firmware", "humanoid", "humanoid-robot", "robotics" ], "pushed_at": "2017-10-19", "created_at": "2017-07-01", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Simone Primarosa", "owner_company": "Boltz | Former: Google, Microsoft, Busrapido", "owner_location": "Zurich, Switzerland.", "owner_url": "https://github.com/simonepri", "owner_repos": 138, "owner_followers": 299, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "worldbench/awesome-agentic-world-model", "slug": "worldbench-awesome-agentic-world-model", "url": "https://github.com/worldbench/awesome-agentic-world-model", "owner": "worldbench", "name": "awesome-agentic-world-model", "description": "\ud83d\udd25 Quo Vadis, World Modeling? Towards Interactive World Proxies for Continually Improving Agents", "readme": "The taxonomy has two orthogonal axes:", "stars": 48, "stars_scraped": 48, "forks": 0, "watchers": 1, "language": null, "license": null, "gh_topics": [ "agent", "agentic", "agentic-ai", "agentic-world-model", "agents", "aigc", "closed-loop", "closed-loop-control", "closed-loop-experiments", "closed-loop-simulation", "generation", "generative-ai", "image-generation", "video-generation", "world-model", "world-modeling", "world-models", "world-models-rl" ], "pushed_at": "2026-08-22", "created_at": "", "archived": false, "paper_ids": [ "2608.02713" ], "owner_type": "Organization", "owner_display": "worldbench", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/worldbench", "owner_repos": 29, "owner_followers": 148, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.02713", "slug": "quo-vadis-world-modeling", "title": "Quo Vadis, World Modeling?", "featured": false } ], "topics": [ "world-models" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "jewel-nath/robot-blueberry", "slug": "jewel-nath-robot-blueberry", "url": "https://github.com/jewel-nath/robot-blueberry", "owner": "jewel-nath", "name": "robot-blueberry", "description": "Raspberry pi based humanoid robot.", "readme": "", "stars": 47, "stars_scraped": 47, "forks": 22, "watchers": 1, "language": "Python", "license": "MIT", "gh_topics": [ "arduino", "diy", "google-api", "humanoid", "humanoid-robot", "humanoid-robotics", "humanoid-robots", "linux", "python", "python-script", "raspberry-pi", "raspberrypi", "robotics", "wake-word-detection" ], "pushed_at": "2021-11-14", "created_at": "2021-04-16", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Jewel Nath", "owner_company": "https://robo-ict.vercel.app/", "owner_location": "Dhaka, Bangladesh", "owner_url": "https://github.com/jewel-nath", "owner_repos": 16, "owner_followers": 115, "owner_bio": "Software Engineer (.NET) | Robotics Explorer", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "humanoids" ], "score": 5, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "Abraham190137/TeleoperationUnity", "slug": "abraham190137-teleoperationunity", "url": "https://github.com/Abraham190137/TeleoperationUnity", "owner": "Abraham190137", "name": "TeleoperationUnity", "description": "", "readme": "The Robotic Control folder contains scripts to interface with the Franka Emika Panda robot, either on hardware through the FrankaPy control structure ( https://github.com/iamlab-cmu/frankapy ) or in simulation, using the PandaGym bybullet based simulator ( https://github.com/qgallouedec/panda-gym ).", "stars": 45, "stars_scraped": 45, "forks": 3, "watchers": 3, "language": null, "license": null, "gh_topics": [], "pushed_at": "2024-12-09", "created_at": "", "archived": false, "paper_ids": [ "2305.09765" ], "owner_type": "User", "owner_display": "Abraham George", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Abraham190137", "owner_repos": 8, "owner_followers": 9, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2305.09765", "slug": "openvr-teleoperation-for-manipulation", "title": "OpenVR: Teleoperation for Manipulation", "featured": false } ], "topics": [ "sim2real", "data-teleop" ], "score": 4, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "cau-hai-lab/LIBERO-Para", "slug": "cau-hai-lab-libero-para", "url": "https://github.com/cau-hai-lab/LIBERO-Para", "owner": "cau-hai-lab", "name": "LIBERO-Para", "description": "Official code for \"LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models\" (EMNLP 2026 Main).", "readme": "1 Soongsil University 2 Chung-Ang University * Equal contribution \u2020 Corresponding author", "stars": 43, "stars_scraped": 43, "forks": 5, "watchers": 2, "language": "Python", "license": "MIT", "gh_topics": [ "benchmark", "embodied-ai", "paraphrase", "robustness", "vision-language-action", "vla" ], "pushed_at": "2026-08-21", "created_at": "2026-03-24", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "cau-hai-lab", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/cau-hai-lab", "owner_repos": 4, "owner_followers": 2, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "safety-eval" ], "score": 4, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "alibaba-damo-academy/RynnWorld-Teleop", "slug": "alibaba-damo-academy-rynnworld-teleop", "url": "https://github.com/alibaba-damo-academy/RynnWorld-Teleop", "owner": "alibaba-damo-academy", "name": "RynnWorld-Teleop", "description": " RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation", "readme": "", "stars": 39, "stars_scraped": 39, "forks": 3, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-03", "created_at": "", "archived": false, "paper_ids": [ "2607.06558" ], "owner_type": "Organization", "owner_display": "Alibaba DAMO Academy", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/alibaba-damo-academy", "owner_repos": 82, "owner_followers": 947, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.06558", "slug": "rynnworld-teleop-an-action-conditioned-world-model-for-digital-teleope", "title": "RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation", "featured": false } ], "topics": [ "world-models", "data-teleop" ], "score": 4, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "InternRobotics/REAL", "slug": "internrobotics-real", "url": "https://github.com/InternRobotics/REAL", "owner": "InternRobotics", "name": "REAL", "description": "[ECCV2026] Official open-source repository for REAL\u2014\u2014Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation", "readme": "REAL is a sim-to-real-consistent framework for interactive open-world mobile manipulation. Agents explore from raw RGB observations, use deployable navigation and manipulation tools, and communicate with a simulated user to resolve ambiguous instructions without privileged simulator information.", "stars": 39, "stars_scraped": 36, "forks": 0, "watchers": 2, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-07-18", "created_at": "", "archived": false, "paper_ids": [ "2607.13653" ], "owner_type": "Organization", "owner_display": "Intern Robotics", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/InternRobotics", "owner_repos": 88, "owner_followers": 1805, "owner_bio": "Building inclusive infrastructure for Embodied AI, from Shanghai AI Lab.", "affiliated_org": "Shanghai AI Lab", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.13653", "slug": "exploratory-communicative-and-deployable-vision-driven-embodied-agents", "title": "Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation", "featured": false } ], "topics": [ "sim2real", "navigation" ], "score": 6, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "ai4ce/INT-ACT", "slug": "ai4ce-int-act", "url": "https://github.com/ai4ce/INT-ACT", "owner": "ai4ce", "name": "INT-ACT", "description": "Official repo for From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models", "readme": "\ud83c\udd95 [2025-6-15] Model Checkpoints Uploaded. Tutorial for Training/Fine-tuning Updated", "stars": 34, "stars_scraped": 33, "forks": 2, "watchers": 4, "language": "Python", "license": null, "gh_topics": [ "benchmarking", "evaluation", "vision-language-action", "vision-language-action-model", "vla" ], "pushed_at": "2025-11-02", "created_at": "2025-06-05", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "AI4CE Lab @ NYU", "owner_company": "", "owner_location": "Brooklyn, NY, U.S.", "owner_url": "https://github.com/ai4ce", "owner_repos": 66, "owner_followers": 282, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "strands-labs/robots-sim", "slug": "strands-labs-robots-sim", "url": "https://github.com/strands-labs/robots-sim", "owner": "strands-labs", "name": "robots-sim", "description": "Simulated environments for robot agent evaluation and reinforcement learning.", "readme": "strands-robots-sim is deprecated and this repository will be archived. The Isaac Sim backend now lives in the strands-labs/robots monorepo as an in-tree builtin backend, so there is no longer a separate plugin package to install.", "stars": 34, "stars_scraped": 34, "forks": 10, "watchers": 4, "language": "Python", "license": "Apache-2.0", "gh_topics": [ "agentic", "agentic-ai", "ai", "genai", "machine-learning", "python", "robots", "simulation", "strands-agents", "strands-labs", "vision-language-action", "vla" ], "pushed_at": "2026-08-06", "created_at": "2026-02-19", "archived": true, "paper_ids": [], "owner_type": "Organization", "owner_display": "strands-labs", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/strands-labs", "owner_repos": 8, "owner_followers": 314, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "rl-control" ], "score": 6, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "Vchitect/RealDPO", "slug": "vchitect-realdpo", "url": "https://github.com/Vchitect/RealDPO", "owner": "Vchitect", "name": "RealDPO", "description": "", "readme": "1 Shanghai Artificial Intelligence Laboratory 2 S-Lab, Nanyang Technological University 3 University of Electronic Science and Technology of China 4 Nanjing University 5 SenseTime Research", "stars": 32, "stars_scraped": 32, "forks": 1, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-18", "created_at": "", "archived": false, "paper_ids": [ "2510.14955" ], "owner_type": "Organization", "owner_display": "Vchitect", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Vchitect", "owner_repos": 37, "owner_followers": 484, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2510.14955", "slug": "realdpo-real-or-not-real-that-is-the-preference", "title": "RealDPO: Real or Not Real, that is the Preference", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "RYNing/Awesome-Post-Training-In-Autonomous-Driving-Papers", "slug": "ryning-awesome-post-training-in-autonomous-driving-papers", "url": "https://github.com/RYNing/Awesome-Post-Training-In-Autonomous-Driving-Papers", "owner": "RYNing", "name": "Awesome-Post-Training-In-Autonomous-Driving-Papers", "description": "A curated list of papers on post-training for end-to-end autonomous driving: distillation, preference alignment, reinforcement learning, and test-time refinement.", "readme": "Post-Training in End-to-End Autonomous Driving: A Unified View Ruining Yang*, Muxing Wang*, Yixiao Chen, Tongfei Guo, Yi Xu, Can Cui, Zichong Yang, Yitian Zhang, Ziran Wang, Yun Fu, Lili Su. (* Equal contribution. Northeastern University & Purdue University.)", "stars": 30, "stars_scraped": 30, "forks": 0, "watchers": 1, "language": null, "license": "NOASSERTION", "gh_topics": [ "autonomous-driving", "awesome", "awesome-list", "end-to-end-driving", "paper-list", "post-training", "reinforcement-learning", "reinforcement-learning-from-human-feedback", "vision-language-action" ], "pushed_at": "2026-07-28", "created_at": "2026-07-12", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "RY-ning", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/RYNing", "owner_repos": 4, "owner_followers": 9, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "rl-control", "navigation" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "dwipddalal/Anchor-Align", "slug": "dwipddalal-anchor-align", "url": "https://github.com/dwipddalal/Anchor-Align", "owner": "dwipddalal", "name": "Anchor-Align", "description": "Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment", "readme": "TL;DR \u2014 Standard behavior-cloning finetuning of a vision-language model on robot demos silently erases the pretrained VLM's semantics and decouples its language output from its actions. Anchor-Align adds two lightweight losses on top of action prediction that (i) anchor the trainable VLA to a frozen copy of the pretrained VLM (preserving vision-language reasoning) and (ii) align the pre-action hid", "stars": 30, "stars_scraped": 25, "forks": 1, "watchers": 1, "language": "Python", "license": "MIT", "gh_topics": [ "behavior-cloning", "calvin", "catastrophic-forgetting", "embodied-ai", "foundation-models", "generalization", "imitation-learning", "knowledge-distillation", "libero", "openvla", "robot-learning", "robot-manipulation", "robotics", "vision-language-action", "vision-language-model", "vla" ], "pushed_at": "2026-08-25", "created_at": "2026-03-12", "archived": false, "paper_ids": [ "2607.13429" ], "owner_type": "User", "owner_display": "Dwip Dalal", "owner_company": "PhD UIUC", "owner_location": "", "owner_url": "https://github.com/dwipddalal", "owner_repos": 87, "owner_followers": 23, "owner_bio": "Learning to build :)", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.13429", "slug": "generalizable-vla-finetuning-via-representation-anchoring-and-language", "title": "Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment", "featured": false } ], "topics": [ "vla", "video-generation" ], "score": 3, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "robosense2025/track2", "slug": "robosense2025-track2", "url": "https://github.com/robosense2025/track2", "owner": "robosense2025", "name": "track2", "description": "Track 2: Social Navigation", "readme": "", "stars": 27, "stars_scraped": 27, "forks": 0, "watchers": 2, "language": null, "license": "Apache-2.0", "gh_topics": [ "embodied-agent", "social-navigation", "vision-language-action", "vision-language-models" ], "pushed_at": "2025-08-19", "created_at": "2025-06-09", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "robosense2025", "owner_company": "", "owner_location": "IROS 2025", "owner_url": "https://github.com/robosense2025", "owner_repos": 13, "owner_followers": 27, "owner_bio": "", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla", "navigation" ], "score": 4, "from_paper": false, "link_strength": "", "stale": true }, { "full_name": "pokaxpoka/rad_procgen", "slug": "pokaxpoka-rad-procgen", "url": "https://github.com/pokaxpoka/rad_procgen", "owner": "pokaxpoka", "name": "rad_procgen", "description": "RAD: Reinforcement Learning with Augmented Data (code for procgen experiments)", "readme": "got to Procgen_Envs", "stars": 19, "stars_scraped": 19, "forks": 6, "watchers": 1, "language": null, "license": null, "gh_topics": [], "pushed_at": "2021-03-29", "created_at": "", "archived": false, "paper_ids": [ "2004.14990" ], "owner_type": "User", "owner_display": "Kimin Lee", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/pokaxpoka", "owner_repos": 26, "owner_followers": 105, "owner_bio": "https://sites.google.com/view/kiminlee", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2004.14990", "slug": "reinforcement-learning-with-augmented-data", "title": "Reinforcement Learning with Augmented Data", "featured": false } ], "topics": [ "rl-control" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "UARK-AICV/OBEYED_VLA", "slug": "uark-aicv-obeyed-vla", "url": "https://github.com/UARK-AICV/OBEYED_VLA", "owner": "UARK-AICV", "name": "OBEYED_VLA", "description": "OBEYED-VLA: Clutter-Resistant Vision-Language-Action Models through Object-Centric and Geometry Grounding", "readme": "", "stars": 14, "stars_scraped": 14, "forks": 0, "watchers": 1, "language": "Python", "license": null, "gh_topics": [ "embodied-ai", "robotics", "vision-language-action", "vision-language-action-model", "vision-language-model", "visuomotor-control" ], "pushed_at": "2026-05-08", "created_at": "2025-12-28", "archived": false, "paper_ids": [], "owner_type": "Organization", "owner_display": "AICV Lab", "owner_company": "", "owner_location": "United States of America", "owner_url": "https://github.com/UARK-AICV", "owner_repos": 43, "owner_followers": 56, "owner_bio": "University of Arkansas EECS", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "miracle-techlink/awesome-vla-2026", "slug": "miracle-techlink-awesome-vla-2026", "url": "https://github.com/miracle-techlink/awesome-vla-2026", "owner": "miracle-techlink", "name": "awesome-vla-2026", "description": "\ud83d\udcda Vision-Language-Action Models \u00b7 2026 categorized index \u2014 250+ papers across 15 categories, synthesized from 11 surveys + 8 awesome lists, with clickable arXiv links", "readme": "VLA \u7684\"\u57fa\u7840\u8bbe\u65bd\"\u2014\u2014\u540e\u9762\u6240\u6709\u67b6\u6784\u90fd\u5728\u8fd9\u6761\u7ebf\u4e0a\u52a0\u4e1c\u897f\u3002RT-1/RT-2 \u628a transformer \u5f15\u5165\u63a7\u5236\uff0cOpenVLA \u5f00\u6e90\u5316\uff0c\u03c00 \u628a flow-matching \u62ff\u6765\u751f\u6210\u8fde\u7eed\u52a8\u4f5c\uff0cOcto / RDT-1B \u662f diffusion \u6d41\u6d3e\u7684\u4ee3\u8868\u3002\u8bfb VLA \u4e0d\u7ed5\u8fc7\u8fd9\u4e00\u7ec4\u3002", "stars": 13, "stars_scraped": 13, "forks": 1, "watchers": 1, "language": null, "license": null, "gh_topics": [ "awesome-list", "embodied-ai", "foundation-models", "paper-list", "robot-learning", "robot-manipulation", "robotics", "survey", "vision-language-action", "vla" ], "pushed_at": "2026-05-29", "created_at": "2026-05-29", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Liu Yue", "owner_company": "Tongji University", "owner_location": "Shanghai ", "owner_url": "https://github.com/miracle-techlink", "owner_repos": 35, "owner_followers": 27, "owner_bio": "robotics researcher/startup", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "rai-opensource/vernata", "slug": "rai-opensource-vernata", "url": "https://github.com/rai-opensource/vernata", "owner": "rai-opensource", "name": "vernata", "description": "", "readme": "We present Vernata, a multi-modal, multi-teacher distillation framework for self-supervised learning on outdoor LiDAR point clouds. Building upon the Sonata architecture, we introduce sparse view augmentation, a memory bank mechanism, and cross-modal distillation using dense, high-resolution 2D image features to enable fine-grained semantic guidance and robust inference across varying point densit", "stars": 15, "stars_scraped": 13, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-11", "created_at": "", "archived": false, "paper_ids": [ "2608.06919" ], "owner_type": "Organization", "owner_display": "RAI Open Source", "owner_company": "Robotics and AI Institute", "owner_location": "United States of America", "owner_url": "https://github.com/rai-opensource", "owner_repos": 50, "owner_followers": 138, "owner_bio": "Open source repositories managed by the Robotics and AI Institute (rai-inst.com)", "affiliated_org": "Boston Dynamics", "link_sources": [ "arxiv-comment", "paper-fulltext" ], "papers": [ { "id": "2608.06919", "slug": "vernata-self-supervised-learning-of-lidar-point-representations", "title": "Vernata: Self-Supervised Learning of LiDAR Point Representations", "featured": false } ], "topics": [ "spatial-3d" ], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "megaknight114/DropVLA", "slug": "megaknight114-dropvla", "url": "https://github.com/megaknight114/DropVLA", "owner": "megaknight114", "name": "DropVLA", "description": "Backdoor training and evaluation scripts for vision-language-action models on LIBERO.", "readme": "[ Paper ] [ Dataset ] [ Citation ]", "stars": 12, "stars_scraped": 11, "forks": 0, "watchers": 0, "language": "Python", "license": "MIT", "gh_topics": [ "backdoor", "libero", "robotics", "vision-language-action" ], "pushed_at": "2026-07-25", "created_at": "2025-08-31", "archived": false, "paper_ids": [], "owner_type": "User", "owner_display": "Zonghuan Xu", "owner_company": "Fudan University", "owner_location": "Shanghai, China", "owner_url": "https://github.com/megaknight114", "owner_repos": 6, "owner_followers": 2, "owner_bio": "Fudan undergraduate | Trustworthy AI, deep learning theory, continual learning theory, and embodied AI.", "affiliated_org": null, "link_sources": [], "papers": [], "topics": [ "vla" ], "score": 5, "from_paper": false, "link_strength": "", "stale": false }, { "full_name": "lzyang2000/cbf-rl-navigation-demo", "slug": "lzyang2000-cbf-rl-navigation-demo", "url": "https://github.com/lzyang2000/cbf-rl-navigation-demo", "owner": "lzyang2000", "name": "cbf-rl-navigation-demo", "description": "", "readme": "The project provides several environment configurations through the UnifiedNavigationEnv by passing different arguments:", "stars": 11, "stars_scraped": 11, "forks": 1, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-03-13", "created_at": "", "archived": false, "paper_ids": [ "2510.14959" ], "owner_type": "User", "owner_display": "Lizhi Yang", "owner_company": "", "owner_location": "Pasadena, CA", "owner_url": "https://github.com/lzyang2000", "owner_repos": 115, "owner_followers": 61, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2510.14959", "slug": "cbf-rl-safety-filtering-reinforcement-learning-in-training-with-contro", "title": "CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions", "featured": false } ], "topics": [ "navigation" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "wanhaoniu/EAGG", "slug": "wanhaoniu-eagg", "url": "https://github.com/wanhaoniu/EAGG", "owner": "wanhaoniu", "name": "EAGG", "description": "Embodiment-Aligned Grasp Generation via Geometry-Aware Graph Conditioning", "readme": "\u4e2d\u6587 | Project Page | Paper | Core Idea | Installation | Quick Start | Training | Visualization | Citation", "stars": 11, "stars_scraped": 11, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-06-19", "created_at": "", "archived": false, "paper_ids": [ "2606.18092" ], "owner_type": "User", "owner_display": "Wanhao Niu", "owner_company": "Shanghai Jiaotong University", "owner_location": "", "owner_url": "https://github.com/wanhaoniu", "owner_repos": 8, "owner_followers": 4, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2606.18092", "slug": "eagg-embodiment-aligned-grasp-generation-via-geometry-aware-graph-cond", "title": "EAGG: Embodiment-Aligned Grasp Generation via Geometry-Aware Graph Conditioning", "featured": false } ], "topics": [ "dexterous-manipulation" ], "score": 5, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "wernerpe/pybmtp", "slug": "wernerpe-pybmtp", "url": "https://github.com/wernerpe/pybmtp", "owner": "wernerpe", "name": "pybmtp", "description": "A python software package for computing smooth, minimum-time trajectories around convex obstacles", "readme": "pybmtp plans time-optimal Bezier trajectories that respect a velocity limit and, optionally, acceleration / jerk / snap limits while avoiding convex obstacles. The package provides:", "stars": 4, "stars_scraped": 4, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-05", "created_at": "", "archived": false, "paper_ids": [ "2608.02834" ], "owner_type": "User", "owner_display": "Peter Werner", "owner_company": "Massachusetts Institute of Technology", "owner_location": "Z\u00fcrich/Cambridge", "owner_url": "https://github.com/wernerpe", "owner_repos": 42, "owner_followers": 30, "owner_bio": "PhD student at CSAIL\r\n\r\n", "affiliated_org": "MIT", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.02834", "slug": "biconvex-optimization-for-smooth-minimum-time-trajectories-around-conv", "title": "Biconvex Optimization for Smooth Minimum-Time Trajectories around Convex Obstacles", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "zheyu-zhuang/seeker", "slug": "zheyu-zhuang-seeker", "url": "https://github.com/zheyu-zhuang/seeker", "owner": "zheyu-zhuang", "name": "seeker", "description": "[Seeker]: Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning", "readme": "Zheyu Zhuang\u00b9 \u00b7 Ruiyu Wang\u00b9 \u00b7 Nick Heppert\u00b2 \u00b7 Johannes Fabian Hahn\u00b3 \u00b7 Abhinav Valada\u00b2 \u00b7 Florian T. Pokorny\u00b9 \u00b7 Danica Kragic\u00b9", "stars": 4, "stars_scraped": 4, "forks": 0, "watchers": 1, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-18", "created_at": "", "archived": false, "paper_ids": [ "2608.13422" ], "owner_type": "User", "owner_display": "Ryan.Z", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/zheyu-zhuang", "owner_repos": 6, "owner_followers": 3, "owner_bio": "Make \ud83e\udd16 see and act!", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.13422", "slug": "attention-from-action-for-action-emergent-visual-bottlenecks-for-polic", "title": "Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning", "featured": false } ], "topics": [], "score": 2, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "damanimc/ImprovedVBGS", "slug": "damanimc-improvedvbgs", "url": "https://github.com/damanimc/ImprovedVBGS", "owner": "damanimc", "name": "ImprovedVBGS", "description": "Improved Variational Bayes Gaussian Splatting", "readme": "", "stars": 3, "stars_scraped": 3, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-10", "created_at": "", "archived": false, "paper_ids": [ "2607.15542" ], "owner_type": "User", "owner_display": "damanimc", "owner_company": "Imperial College London", "owner_location": "London", "owner_url": "https://github.com/damanimc", "owner_repos": 24, "owner_followers": 12, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.15542", "slug": "improvedvbgs-real-time-continual-variational-bayes-gaussian-splatting", "title": "ImprovedVBGS: Real-time Continual Variational Bayes Gaussian Splatting", "featured": false } ], "topics": [ "spatial-3d" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "Akshay5312/paamp_underactuated", "slug": "akshay5312-paamp-underactuated", "url": "https://github.com/Akshay5312/paamp_underactuated", "owner": "Akshay5312", "name": "paamp_underactuated", "description": "Trusted Polytopic Action Sets for fast underactuated motion planning", "readme": "1 \u00b7 Linearize around a nominal trajectory. Given a nominal feasible motion (x*(t), u*(t)) , the LTV linearization maps a finite parameter vector \u03b3 to a whole nearby trajectory:", "stars": 1, "stars_scraped": 1, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-06", "created_at": "", "archived": false, "paper_ids": [ "2608.24019" ], "owner_type": "User", "owner_display": "Akshay Jaitly", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Akshay5312", "owner_repos": 23, "owner_followers": 8, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.24019", "slug": "trusted-polytopic-action-sets-for-fast-planning-in-underactuated-syste", "title": "Trusted Polytopic Action Sets for Fast Planning in Underactuated Systems", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "Dzxx623/TAMS", "slug": "dzxx623-tams", "url": "https://github.com/Dzxx623/TAMS", "owner": "Dzxx623", "name": "TAMS", "description": "ROS 2 reference implementation of Task-Aware Multi-View Adaptive Streaming for wireless telerobotic manipulation.", "readme": "Rende, Italy, September 7\u201311, 2026.", "stars": 1, "stars_scraped": 1, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-10", "created_at": "", "archived": false, "paper_ids": [ "2608.09731" ], "owner_type": "User", "owner_display": "Zexin Deng", "owner_company": "University of Warwick", "owner_location": "Coventry, CV4 7AL, United Kingdom", "owner_url": "https://github.com/Dzxx623", "owner_repos": 4, "owner_followers": 0, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.09731", "slug": "tams-task-aware-multi-view-adaptive-streaming-for-wireless-telerobotic", "title": "TAMS: Task-Aware Multi-View Adaptive Streaming for Wireless Telerobotic Manipulation", "featured": false } ], "topics": [], "score": 2, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "Lasan-Perera/6-dof-arm-neuralnexus", "slug": "lasan-perera-6-dof-arm-neuralnexus", "url": "https://github.com/Lasan-Perera/6-dof-arm-neuralnexus", "owner": "Lasan-Perera", "name": "6-dof-arm-neuralnexus", "description": "6_DoF_Arm NeuralNexus is a six-degree-of-freedom robotic arm designed for precise object manipulation and automation tasks. It provides flexible movement, accurate positioning, and is suitable for robotics research, AI applications, and pick-and-place operations.", "readme": "A fully custom 6-axis robotic arm \u2014 not a kit . Every layer was designed, debugged, and integrated in-house:", "stars": 1, "stars_scraped": 1, "forks": 2, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-08", "created_at": "", "archived": false, "paper_ids": [ "2608.22799" ], "owner_type": "User", "owner_display": "Lasan Perera ", "owner_company": "", "owner_location": "Sri Lanka ", "owner_url": "https://github.com/Lasan-Perera", "owner_repos": 16, "owner_followers": 8, "owner_bio": "Electronic & Telecommunication Engineering undergrad @ University of Moratuwa. Robotics, embedded systems, PCB design & control. Building things that move.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.22799", "slug": "reproducible-vision-guided-6-dof-robotic-manipulator-with-a-mixed-step", "title": "Reproducible Vision-Guided 6-DoF Robotic Manipulator with a Mixed Stepper-Driver Architecture and Browser-Native Control", "featured": false } ], "topics": [], "score": 6, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "CoMMALab/anytime_gtmp", "slug": "commalab-anytime-gtmp", "url": "https://github.com/CoMMALab/anytime_gtmp", "owner": "CoMMALab", "name": "anytime_gtmp", "description": "Anytime Global Tensor Motion Planning", "readme": "", "stars": 0, "stars_scraped": null, "forks": null, "watchers": null, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-27", "created_at": "", "archived": false, "paper_ids": [ "2608.25830" ], "owner_type": null, "owner_display": null, "owner_company": "", "owner_location": "", "owner_url": "https://github.com/CoMMALab", "owner_repos": null, "owner_followers": null, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.25830", "slug": "anytime-global-tensor-motion-planning", "title": "Anytime Global Tensor Motion Planning", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "SDNT8810/safe-actor-critic-aer-ue-reproducibility", "slug": "sdnt8810-safe-actor-critic-aer-ue-reproducibility", "url": "https://github.com/SDNT8810/safe-actor-critic-aer-ue-reproducibility", "owner": "SDNT8810", "name": "safe-actor-critic-aer-ue-reproducibility", "description": "", "readme": "Toward Integrating Adaptive Experience Replay and Online Uncertainty Estimation in Safe Actor-Critic Optimal Control", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-07-23", "created_at": "", "archived": false, "paper_ids": [ "2608.04732" ], "owner_type": "User", "owner_display": "Davoud Nikkhouy", "owner_company": "Freelancer", "owner_location": "Milan, Italy", "owner_url": "https://github.com/SDNT8810", "owner_repos": 28, "owner_followers": 11, "owner_bio": "Mechatronic and Embedded Developer", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.04732", "slug": "toward-integrating-adaptive-experience-replay-and-online-uncertainty-e", "title": "Toward Integrating Adaptive Experience Replay and Online Uncertainty Estimation in Safe Actor-Critic Optimal Control", "featured": false } ], "topics": [ "rl-control" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "Su-ISE-2001/LabRobFail", "slug": "su-ise-2001-labrobfail", "url": "https://github.com/Su-ISE-2001/LabRobFail", "owner": "Su-ISE-2001", "name": "LabRobFail", "description": "LabRobFail: A Benchmark for Robotic Failure Analysis in Scientific and Self-driving Laboratory", "readme": "\u8fd9\u4e9b\u5f02\u5e38\u914d\u7f6e\u53ef\u7528\u4e8e\uff1a", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-07-27", "created_at": "", "archived": false, "paper_ids": [ "2607.23704" ], "owner_type": "User", "owner_display": "PLANB", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/Su-ISE-2001", "owner_repos": 8, "owner_followers": 0, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.23704", "slug": "labrobfail-a-benchmark-for-robotic-failure-analysis-in-chemical-self-d", "title": "LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratory", "featured": false } ], "topics": [ "sim2real" ], "score": 5, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "UoA-CARES/instant-episode-repetition", "slug": "uoa-cares-instant-episode-repetition", "url": "https://github.com/UoA-CARES/instant-episode-repetition", "owner": "UoA-CARES", "name": "instant-episode-repetition", "description": "Official implementation of Instant Episode Repetition (IER) for sample-efficient reinforcement learning with SAC and TD3.", "readme": "", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-25", "created_at": "", "archived": false, "paper_ids": [ "2608.17347" ], "owner_type": "Organization", "owner_display": "CARES", "owner_company": "", "owner_location": "University of Auckland ", "owner_url": "https://github.com/UoA-CARES", "owner_repos": 73, "owner_followers": 38, "owner_bio": "UoA Centre of Automation and Robotic Engineer Science", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.17347", "slug": "repetition-as-reinforcement-enhancing-sample-efficiency-via-instant-ep", "title": "Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning", "featured": false } ], "topics": [ "rl-control" ], "score": 1, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "a-pru/descent", "slug": "a-pru-descent", "url": "https://github.com/a-pru/descent", "owner": "a-pru", "name": "descent", "description": "[IROS 2026] DESCENT: Directed Edge Scene Encoding for Airport Surface Movement Prediction", "readme": "", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-27", "created_at": "", "archived": false, "paper_ids": [ "2608.26002" ], "owner_type": "User", "owner_display": "Alexander Prutsch", "owner_company": "Graz University of Technology", "owner_location": "Graz", "owner_url": "https://github.com/a-pru", "owner_repos": 7, "owner_followers": 0, "owner_bio": "Visual Computing PhD Student", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.26002", "slug": "descent-directed-edge-scene-encoding-for-airport-surface-movement-pred", "title": "DESCENT: Directed Edge Scene Encoding for Airport Surface Movement Prediction", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "arifence2024/DynamicSpectraFormer", "slug": "arifence2024-dynamicspectraformer", "url": "https://github.com/arifence2024/DynamicSpectraFormer", "owner": "arifence2024", "name": "DynamicSpectraFormer", "description": "", "readme": "", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 1, "language": null, "license": null, "gh_topics": [], "pushed_at": "2024-03-14", "created_at": "", "archived": false, "paper_ids": [ "2608.18662" ], "owner_type": "User", "owner_display": "arifence2024", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/arifence2024", "owner_repos": 2, "owner_followers": 1, "owner_bio": "", "affiliated_org": null, "link_sources": [ "paper-fulltext" ], "papers": [ { "id": "2608.18662", "slug": "dynamic-spectraformer-for-ultra-high-definition-underwater-image-enhan", "title": "Dynamic SpectraFormer for Ultra-High-Definition Underwater Image Enhancement", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "named-after-paper", "stale": false }, { "full_name": "be2rlab/OSMa-Bench-v2", "slug": "be2rlab-osma-bench-v2", "url": "https://github.com/be2rlab/OSMa-Bench-v2", "owner": "be2rlab", "name": "OSMa-Bench-v2", "description": "", "readme": "Links: Preprint \u00b7 Project page", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-06-09", "created_at": "", "archived": false, "paper_ids": [ "2605.26831" ], "owner_type": "Organization", "owner_display": "ITMO Biomechatronics and Energy Efficient Robotics Laboratory", "owner_company": "", "owner_location": "Saint Petersburg", "owner_url": "https://github.com/be2rlab", "owner_repos": 35, "owner_followers": 55, "owner_bio": "Laboratory of Biomechatronics and Energy-Efficient Robotics at ITMO University", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2605.26831", "slug": "osma-bench-toward-open-ended-benchmarking-of-semantic-mapping-for-mani", "title": "OSMa-Bench++: Toward Open-Ended Benchmarking of Semantic Mapping for Manipulation with Prompt-Generated Synthetic Scenes", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "bhattner143/SINDYc_MPC_RoSE_symmetric_peristaltic", "slug": "bhattner143-sindyc-mpc-rose-symmetric-peristaltic", "url": "https://github.com/bhattner143/SINDYc_MPC_RoSE_symmetric_peristaltic", "owner": "bhattner143", "name": "SINDYc_MPC_RoSE_symmetric_peristaltic", "description": "This repo is for raspberry pi only", "readme": "The following script in the root folder can be run for Offline MPC simulation (model as plant, no hardware)", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 1, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-04-03", "created_at": "", "archived": false, "paper_ids": [ "2608.09602" ], "owner_type": "User", "owner_display": "Dipankar Bhattacharya", "owner_company": "Imperial College London", "owner_location": "London", "owner_url": "https://github.com/bhattner143", "owner_repos": 22, "owner_followers": 3, "owner_bio": "Dr Dipankar Bhattacharya is a Marie\u202fSk\u0142odowska\u2011Curie Fellow at the Dyson School of Design Engineering, Imperial College\u202fLondon.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.09602", "slug": "nonlinear-model-predictive-control-of-a-robotic-soft-esophagus", "title": "Nonlinear Model Predictive Control of a Robotic Soft Esophagus", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "calumarnott/mujoco", "slug": "calumarnott-mujoco", "url": "https://github.com/calumarnott/mujoco", "owner": "calumarnott", "name": "mujoco", "description": "Multi-Joint dynamics with Contact. A general purpose physics simulator. This fork implements a custom gradient backend for implicit differentiation of the contact solver residual..", "readme": "\ud83d\udd27 Fork note (3.9.0) \u2013 This is a fork of MuJoCo that adds switchable, reverse-mode-stable derivatives to the MJX solver. The upstream solver relies on jax.lax.while_loop , which is not reverse-mode compatible beyond the first iteration (XLA requires static memory bounds). In practice, due to lack of convergence, we observed exploding gradients and ill-conditioned Jacobians, leading to unstable lear", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-03", "created_at": "", "archived": false, "paper_ids": [ "2607.24959" ], "owner_type": "User", "owner_display": "Calum Arnott", "owner_company": "", "owner_location": "Edinburgh, Scotland, UK", "owner_url": "https://github.com/calumarnott", "owner_repos": 19, "owner_followers": 0, "owner_bio": "Robotics PhD @ University of Edinburgh\r\n\r\nCo-founder @ Lerta Ltd\r\n\r\nBuilding software and hardware for robotics and autonomous systems", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2607.24959", "slug": "amortising-trajectory-optimisation-for-residual-mpc-via-implicit-conta", "title": "Amortising Trajectory Optimisation for Residual MPC via Implicit Contact Differentiation", "featured": false } ], "topics": [ "sim2real" ], "score": 5, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "marmotlab/PCDP", "slug": "marmotlab-pcdp", "url": "https://github.com/marmotlab/PCDP", "owner": "marmotlab", "name": "PCDP", "description": "", "readme": "", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-17", "created_at": "", "archived": false, "paper_ids": [ "2608.16229" ], "owner_type": "Organization", "owner_display": "MARMot Lab @ NUS-ME", "owner_company": "", "owner_location": "National University of Singapore (NUS)", "owner_url": "https://github.com/marmotlab", "owner_repos": 54, "owner_followers": 304, "owner_bio": "MultiAgent Robotic MOTion laboratory at the National University of Singapore", "affiliated_org": "NUS", "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.16229", "slug": "planner-conditioned-diffusion-for-coordinated-multi-agent-exploration", "title": "Planner-Conditioned Diffusion for Coordinated Multi-Agent Exploration", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "ruancarminati/MAGIC-HRI-V01", "slug": "ruancarminati-magic-hri-v01", "url": "https://github.com/ruancarminati/MAGIC-HRI-V01", "owner": "ruancarminati", "name": "MAGIC-HRI-V01", "description": "", "readme": "The dataset includes recordings from 11 participants performing a series of predefined tasks and gestures. A total of 53 movement classes were defined. Each participant contributed 10 samples per class, resulting in 530 samples and approximately 57 minutes of raw data per individual.", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-19", "created_at": "", "archived": false, "paper_ids": [ "2608.21620" ], "owner_type": "User", "owner_display": "ruancarminati", "owner_company": "", "owner_location": "", "owner_url": "https://github.com/ruancarminati", "owner_repos": 2, "owner_followers": 0, "owner_bio": "", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.21620", "slug": "why-personalization-matters-cross-subject-challenges-in-emg-imu-based", "title": "Why Personalization Matters: Cross-Subject Challenges in EMG-IMU-based HRI Activity Recognition", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false }, { "full_name": "yashbagla321/excitation-supervised-closed-loop", "slug": "yashbagla321-excitation-supervised-closed-loop", "url": "https://github.com/yashbagla321/excitation-supervised-closed-loop", "owner": "yashbagla321", "name": "excitation-supervised-closed-loop", "description": "", "readme": "u = u_seek + u_exp(t) , with u_exp(t) = A e^{-lambda(t - t0)} [cos(omega t), sin(omega t)]^T a decaying circular excitation whose epoch t0 resets whenever the stored window's trajectory spread S_v (computed from the known measurement poses) falls below the threshold S_bar (Algorithm 1 in the paper). While the window is underexcited, the nominal seeking velocity -k(q - p_hat) is projected onto the ", "stars": 0, "stars_scraped": 0, "forks": 0, "watchers": 0, "language": null, "license": null, "gh_topics": [], "pushed_at": "2026-08-14", "created_at": "", "archived": false, "paper_ids": [ "2608.12528" ], "owner_type": "User", "owner_display": "Yash Bagla", "owner_company": "", "owner_location": "East Lansing, United States", "owner_url": "https://github.com/yashbagla321", "owner_repos": 19, "owner_followers": 0, "owner_bio": "Engineer. Researcher. Dancer. Voyager.", "affiliated_org": null, "link_sources": [ "arxiv-comment" ], "papers": [ { "id": "2608.12528", "slug": "excitation-supervised-closed-loop-self-calibration-and-target-seeking", "title": "Excitation-Supervised Closed-Loop Self-Calibration and Target Seeking for an Unknown-Pose Range-Bearing Relay", "featured": false } ], "topics": [], "score": 0, "from_paper": true, "link_strength": "endorsed", "stale": false } ]