2025-09-23 · NeurIPS · 30 citations · club pick

EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data

Ryan Punamiya, Dhruv Patel, Patcharapong Aphiwetsa, Pranav Kuppili, Lawrence Y. Zhu, Simar Kareer, Judy Hoffman, Danfei Xu

arXiv abstract PDF HTML DOI

Published at NeurIPS (the arXiv record still lists it as a preprint). 30 citations, 2 of them influential, as of the last refresh.

Abstract

Egocentric human experience data presents a vast resource for scaling up end-to-end imitation learning for robotic manipulation. However, significant domain gaps in visual appearance, sensor modalities, and kinematics between human and robot impede knowledge transfer. This paper presents EgoBridge, a unified co-training framework that explicitly aligns the policy latent spaces between human and robot data using domain adaptation. Through a measure of discrepancy on the joint policy latent features and actions based on Optimal Transport (OT), we learn observation representations that not only align between the human and robot domain but also preserve the action-relevant information critical for policy learning. EgoBridge achieves a significant absolute policy success rate improvement by 44% over human-augmented cross-embodiment baselines in three real-world single-arm and bimanual manipulation tasks. EgoBridge also generalizes to new objects, scenes, and tasks seen only in human data, where baselines fail entirely. Videos and additional information can be found at https://ego-bridge.github.io

arXiv comment: Accepted at 39th Conference on Neural Information Processing Systems (NeurIPS 2025) and Oral at Conference on Robot Learning (CoRL 2025)

Ten-minute slide kit

Six slides is the whole talk: what was broken, what people tried, what these authors did, what the numbers say, where it falls over, and the sentence people should remember.

SLIDE 1

The problem

Supervised imitation learning methods such as behavior cloning have emerged as a promising path to scaling robot performance across diverse objects, tasks, and environments. However, while large-scale models in vision and language have achieved remarkable generalization through Internet-sourced data, replicating this success in robotics remains challenging due to the labor-intensive nature of collecting teleoperated demonstrations. Deploying physical robots to many new environments to collect data with enough…

SLIDE 2

What came before

Supervised Imitation Learning (SIL), notably Behavior Cloning, leverages expert demonstrations for policy learning and has achieved significant success in robotics, particularly with large-scale datasets \[5, 6, 7, 8, 9, 10, 11, 12, 13, [14\]](#page-10-2). State-of-the-art Vision-Language-Action (VLA) models \[10, 8, 12, [11\]](#page-9-10) integrate Vision-Language Models (VLMs) with action decoders, enhancing generalization by incorporating semantic understanding from internetscale data. Despite these advances,…

SLIDE 3

The method

The following section describes how fϕ and πθ are parameterized in the simulation and real-world experiments. All hyperparameters are summarized in Table 3, Table 4 for real-world and in Table 5 for

SLIDE 4

What they measured

In this section, we aim to validate three core hypotheses. H1: EgoBridge improves co-training performance for scenarios present in both human and robot data. H2: EgoBridge enables generalization to scenarios only seen in human data. H3: EgoBridge learns a shared latent space where human and robot data are aligned in task-relevant

SLIDE 5

Where it breaks

We presented EgoBridge, a novel co-training framework designed to enable robots to learn effectively from egocentric human data by explicitly addressing domain gaps. By leveraging Optimal Transport on joint policy latent feature-action distributions, guided by Dynamic Time Warping cost on action trajectories, EgoBridge successfully aligns human and robot representations while preserving critical action-relevant information. Our experiments demonstrated significant improvements in real-world task success rates (up…

SLIDE 6

One-line takeaway

Pretrains Transformer robot policies on large-scale human behavioral data, then adapts to downstream robotic tasks with low-shot finetuning.

Assembled from the paper's own PDF, parsed with its layout intact, 87,440 characters of it, then split on the paper's own section headings. Extractive, not generated: every sentence here is lifted from the paper. The takeaway line is the club's own one-liner from its reading list. Check it before you present it.

Figures worth putting on a slide

Figure 1: EgoBridge enables rich knowledge transfer from human to robot, based on our key hypothesis: aligned latent representations yield stronger transfer. Our algorithm, which a
Figure 2: EgoBridge policy co-training with joint adaptation. The encoder fϕ consists of modalityspecific input stems and the encoder trunk, while the policy πθ</su
Figure 3: In the simulated Push-T experiments, we probe a toy version of visual and motion level generalization from human to robot. We have narrow target "robot" data represented
Figure 4: Training Data and Evaluation Settings. We show the distribution of human and robot training data (top) and evaluation setting, where in-distribution scenarios are in both
Figure 5: Visualization of TSNE plots on encoded features for EgoBridge and baselines, with the mean Wasserstein-2 distance and KNN pairs of aligned human-robot data visualized.
Figure 6: We employ the Aria glasses to capture Egocentric RGB images for both human and robot embodiments. The Aria uses its side SLAM cameras to estimate device pose and hand tra

Presented at

Saturday, May 16, 2026

Saturday Robotics, session 8

Robotics & World Models Reading Club 08: Embodied Human Data as the “Internet of Motion and Behavior” — San Francisco 0516

Listed on the event page as “Scaling Robot Learning with Human Behavior Priors”. The arXiv title above is the record.

San Francisco, CA

Saturday, June 20, 2026

Saturday Robotics, session 13

Robotics & World Models Reading Club 13: HumanEgo: Train Robot Policy from 30 min Egocentric Videos — SF 0620