4 papers
ARM: Advantage Reward Modeling for Long-Horizon Manipulation
Yiming Mao, Zixi Yu, Weixin Mao +5
Long-horizon robotic manipulation remains challenging for reinforcement learning (RL) because sparse rewards provide limited guidance for credit assignment. Practical policy improv…
BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model
Haosheng Li, Weixin Mao, Zihan Lan +6
Vision-Language-Action (VLA) models have achieved significant breakthroughs by leveraging Large Vision Language Models (VLMs) to jointly interpret instructions and visual inputs. H…
BFA: Best-Feature-Aware Fusion for Multi-View Fine-grained Manipulation
Zihan Lan, Weixin Mao, Haosheng Li +4
In real-world scenarios, multi-view cameras are typically employed for fine-grained manipulation tasks. Existing approaches (e.g., ACT) tend to treat multi-view features equally an…
RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World
Weixin Mao, Weiheng Zhong, Zhou Jiang +8
Existing robot policies predominantly adopt the task-centric approach, requiring end-to-end task data collection. This results in limited generalization to new tasks and difficulti…