3 papers
cs.RO2026
INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models
Junhan Sun, Hao Zhao, Guofeng Zhang
Forward latent world models predict how actions change a scene, but recover actions for a desired change only through expensive test-time search. We introduce INTACT (INtent-To-ACT…
cs.CV2026
LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation
Jingjing Wang, Zhengdong Hong, Chong Bao +3
Human-like generalization in open-world remains a fundamental challenge for robotic manipulation. Existing learning-based methods, including reinforcement learning, imitation learn…
cs.CV2026
R3D: Revisiting 3D Policy Learning
Zhengdong Hong, Shenrui Wu, Haozhe Cui +8
3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindered by training instabilities and severe overfitting, precluding the a…