Author

Haodong Yan

Author of 6 papers in this index, working on video & generative modeling and world models.

6papers in this index

—career papers

—citations

—h-index

Identified by Semantic Scholar author 2321603038 on the paper records, so a namesake does not share this page. Career figures are that profile's and are not on file yet.

Papers in this index

2026-08-09

SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models

Junjie He, Junfeng Li, Zhide Zhong +9

Video & generative modeling

2026-08-08

4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields

Lishan Yang, Wenxuan Song, Xi Wang +14

World models Safety & evaluation

2026-08-07

Is Forward Prediction Enough? Physical State Grounding for JEPA World Models

Haodong Yan, Jiaguan Zhu, Mingyuan Jia +12 · 2 citations

World models

2026-08-06

DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation

Junfeng Li, Junjie He, Zhide Zhong +12

Vision-language-action Foundation models & pretraining

2026-08-06

Robust-WAM: Bridging Generative Pretraining and Semantic Foresight in World-Action Models

Haodong Yan, Junfeng Li, Junjie He +12

Simulation, sim-to-real & benchmarks Foundation models & pretraining

2026-07-15

GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

GigaWorld Team, Angen Ye, Angyuan Ma +26 · 1 citation

World models Foundation models & pretraining

Works with

Junjie He Haoang Li Junfeng Li Zhide Zhong Jiaguan Zhu Yangyang Zheng Tianran Zhang Wen Chen Wenxuan Song Yuxiang Gao

Co-authors on the papers above, most frequent first. Linked names have a page here.

Works on

Video & generative modeling World models Foundation models & pretraining Safety & evaluation