Egocentric action transfer aims to decouple the semantic action from egocentric observations and reproduce them in new visual contexts, enabling scalable world simulation, embodied policy learning, and robotic data generation. Existing approaches to transferring actions rely on condition-guided video generation, which...
Yue Ma, Peng-Jie Song, Xinyu Wang et al.· 0 citations
ArticulateArena is proposed, a representation-invariant counterpart of Chamfer distance for articulation that compares the motions one-DOF joints induce rather than the parameters that encode them, and it is proved that the resulting quotient distance is a metric.
Yu-Meng He, Yong-Fei She, Huan-Yu Chen et al.· 0 citations
The method combines chunk-wise autoregressive adaptation, Source-Anchored Distribution Matching Distillation, and Long-Horizon Autoregressive Distillation to reduce train--inference mismatch, preserve source fidelity during two-step generation, and mitigate accumulated temporal drift.
Yi-Cheng Xiao, Wenxun Dai, Xinran Qin et al.· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.