6 papers
RecastVLA: From Past Interaction to Future Control with Adaptive Policy States
Wenbo Li, Jun Yang, Yiteng Chen +2
Sequential manipulation requires a robot to track what has already happened, even when the current scene no longer reveals it. Policies with explicit history representations make p…
SCULPT-VLA: Learning Structured Control through Staged Action Grounding
Wenbo Li, Yiteng Chen, Wei Zhang +3
Vision-language-action (VLA) policies increasingly incorporate structured intermediate supervision beyond action labels. Yet specifying what an intermediate representation should e…
Decompose and Reorganize: Planning with Primitives and Visuomotor Policies Learned from Demonstrations
Yizhou Chen, Hang Xu, Dongjie Yu +7
Successfully automating dexterous, long-horizon robotic manipulation requires frameworks capable of both high-level reasoning and fine-grained execution. Traditional task and motio…
SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation
Kaijun Wang, Zikai Ouyang, Xuping Wu +6
Real-world robotic manipulation demands spatial grounding, task-aware reasoning, and precise control. Learning such capabilities becomes particularly challenging in the low-data re…
MinInter: Minimizing Trajectory Interpolation During Data Augmentation for Imitation Learning
Qingyang Wang, Xingang Liu, Changwei Yao +4
Imitation learning enables robots to acquire complex manipulation skills from demonstrations, but its effectiveness is limited by the cost of collecting high-quality data. Trajecto…
From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data
Linfang Zheng, Zikai Ouyang, Chen Wang +2
Video is a scalable observation of physical dynamics: it captures how objects move, how contact unfolds, and how scenes evolve under interaction -- all without requiring robot acti…