Author

Tong Yang

h-index 7 View on Semantic Scholar

We have 1 of 18 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

EDAR: Learning Environment-Dependent Action Representations for Robotic Manipulation

Experiments on simulated and real-robot manipulation benchmarks demonstrate that EDAR improves downstream policy learning, especially in long-horizon manipulation, highlighting the importance of grounding action representations in executable control structure and environment-conditioned visual change.

Yuecheng Xu, Tong Yang, Jingkai Jia et al. · 0 citations