6 papers
ReAP: From Visual Failure Recognition to Action-Conditioned Risk Prediction for Runtime Failure Monitoring
Jingyuan Liu, Yunpeng Qing, Changxu Wei +1
Despite rapid progress, generalist robot policies remain brittle during execution. Reliable deployment therefore requires runtime monitoring that provides timely warnings of failur…
StateSkill-Agent: An Effective and Efficient Embodied Agent via State-conditioned Skill
Changxu Wei, Jingyi Zhang, Zhiyu Zheng +6
In this work, we aim to develop an embodied MLLM agent that understands and solves embodied tasks by learning, abstracting, and reusing transferrable and generalizable behavioral p…
PF-RL: Progress Field Reinforcement Learning via Goal-Conditioned Value Geometry for Vision-Language-Action Models
Yunpeng Qing, Yilun Kong, Sixu Lin +9
Reinforcement Fine-Tuning~(RFT) has emerged as a promising paradigm for improving Vision-Language-Action~(VLA) policies, yet sparse task-level outcomes provide limited credit for i…
Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents
Yixian Zhang, Huanming Zhang, Feng Gao +14
Language-conditioned manipulation requires both precise contact-rich control and robust reasoning over language, scenes, and long horizons. End-to-end Vision-Language-Action (VLA)…
OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models
Tianyi Lin, Chuanyu Sun, Jingyi Zhang +6
Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw. In this work, we aim to develop a framew…
Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning
Yixian Zhang, Huaze Tang, Changxu Wei +1
The Soft Actor-Critic (SAC) algorithm, a state-of-the-art method in maximum entropy reinforcement learning, traditionally relies on minimizing reverse Kullback-Leibler (KL) diverge…