MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning Paper • 2509.22281 • Published Sep 26 • 31
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification Paper • 2508.05629 • Published Aug 7 • 180
Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data Paper • 2507.07095 • Published Jul 9 • 54
SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations Paper • 2505.02094 • Published May 4 • 19
