Diffusion policies are increasingly used in robotic control and manipulation, vision-language-action models, and world-model-based agents. Their ability to represent multimodal action distributions offers rich opportunities for exploration in reinforcement learning (RL). However, optimizing diffusion policies with RL c...
Shu-Tong Ding, Zhao-Yang Liu, Yi-Miao Zhou et al.· 1 citation
Experiments show that FACT improves geometric reconstruction over baselines, enables more reliable interaction with simpler collision proxies, and better reproduces held-out physical responses than direct parameter inference.
Kui-Xiang Shao, Chuan-Sen Nie, Yi-Nuo Bai et al.· 0 citations
PASSAGE, a perception-conditioned planner--tracker framework for humanoid traversal, using virtual reality and inertial motion capture to collect 100 h of scene-aligned human motion across 1,500 cluttered scenes and tests across 50 unseen physical layouts demonstrate traversal without prebuilt maps or offboard computat...