8 papers
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…
Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning
Daoyi Li, Yixian Zhang, Wenbo Ding +2
Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction. However, directly reusing an…
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)…
STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning
Zhihao Liu, Qiuyi Gu, Yitao Wang +16
Real-world robot learning increasingly relies on heterogeneous data, but demonstrations and rollouts often mix useful progress with stalls, corrections, and suboptimal behavior. Ef…
CXR-ContraBench: Benchmarking Negated-Option Attraction in Medical VLMs
Zhengru Fang, Yanan Ma, Yu Guo +5
When a chest X-ray shows consolidation but the question asks which finding is present, a medical vision-language model may answer "No consolidation." This is more than an incorrect…
SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
Yixian Zhang, Shu'ang Yu, Tonghe Zhang +6
Training expressive flow-based policies with off-policy reinforcement learning is notoriously unstable due to gradient pathologies in the multi-step action sampling process. We tra…
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…
Policy Newton Algorithm in Reproducing Kernel Hilbert Space
Yixian Zhang, Huaze Tang, Chao Wang +1
Reinforcement learning (RL) policies represented in Reproducing Kernel Hilbert Spaces (RKHS) offer powerful representational capabilities. While second-order optimization methods l…