5 papers
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
Lichao Wang, Zhaoxing Ren, Tianzhuo Yang +4
As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents u…
STARRY: Spatial-Temporal Action-Centric World Modeling for Robotic Manipulation
Yuxuan Tian, Yurun Jin, Bin Yu +5
Robotic manipulation requires reasoning about future spatial-temporal interactions and geometric constraints, yet existing Vision-Language-Action (VLA) policies often leave predict…
Real-world Reinforcement Learning from Suboptimal Interventions
Yinuo Zhao, Huiqian Jin, Lechun Jiang +9
Real-world reinforcement learning (RL) offers a promising approach to training precise and dexterous robotic manipulation policies in an online manner, enabling robots to learn fro…
HACTS: a Human-As-Copilot Teleoperation System for Robot Learning
Zhiyuan Xu, Yinuo Zhao, Kun Wu +5
Teleoperation is essential for autonomous robot learning, especially in manipulation tasks that require human demonstrations or corrections. However, most existing systems only off…
Training-free Generation of Temporally Consistent Rewards from VLMs
Yinuo Zhao, Jiale Yuan, Zhiyuan Xu +6
Recent advances in vision-language models (VLMs) have significantly improved performance in embodied tasks such as goal decomposition and visual comprehension. However, providing a…