3 papers
cs.AI2026
Learning after Execution with Action-Specific Credit
Yufeng Tian, Jiahao Tang, Minghao Wu
Execution is often used as terminal feedback: it scores a generated program, but the resulting state is not used for another learning action. Learning after execution instead uses…
cs.RO2026
ViTaS: Visual Tactile Soft Fusion Contrastive Learning for Visuomotor Learning
Yufeng Tian, Shuiqi Cheng, Tianming Wei +6
Tactile information plays a crucial role in human manipulation tasks and has recently garnered increasing attention in robotic manipulation. However, existing approaches mostly foc…
cs.RO2025
HDP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning
Yiyang Lu, Yufeng Tian, Zhecheng Yuan +4
Visuomotor policy learning has witnessed substantial progress in robotic manipulation, with recent approaches predominantly relying on generative models to model the action distrib…