8 papers
What Limits Cross-Task Generalization in World Action Models?
Chen Zhao, Zipeng Ye, Yihan Lin +2
Cross-task generalization remains difficult for world action models (WAMs), even when their predicted futures depict plausible manipulation. This gap can be attributed directly: we…
Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies
Chen Zhao, Zipeng Ye, Haitao Shen +3
Test-time sampling promises to turn one action prediction into a set of distinct executable candidates that a verifier can choose among. Downstream fine-tuning works against that p…
JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling
Yihan Lin, Jiawei He, Shifeng Bao +6
Robust robot control benefits from explicitly modeling state transitions, but video-generation world action models (WAMs) introduce substantial deployment cost. Existing latent WAM…
Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision
Haoyang Li, Guanlin Li, Youhe Feng +9
Cross-embodiment transfer in vision-language-action (VLA) models remains challenging because low-level state and action spaces differ fundamentally across robot platforms. We obser…
Harnessing LLM Agents with Skill Programs
Hongjun Liu, Yifei Ming, Shafiq Joty +1
Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lesso…
The Unlearnability Phenomenon in RLVR for Language Models
Yulin Chen, He He, Chen Zhao
Reinforcement Learning with Verifiable Reward (RLVR) has proven effective in improving Large Language Model's (LLM) reasoning ability. However, the learning dynamics of RLVR remain…
TokenPB: Enabling VLA Action Self-Verification via VLM Token Probability Bucketing
Chen Zhao, Zhuoran Wang, Haoyang Li +6
Test-time sampling can improve Vision-Language-Action (VLA) policies, but only if the model can efficiently select a good action from multiple candidates. Prior work often relies o…
Solving Continual Offline Reinforcement Learning with Decision Transformer
Kaixin Huang, Li Shen, Chen Zhao +2
Continuous offline reinforcement learning (CORL) combines continuous and offline reinforcement learning, enabling agents to learn multiple tasks from static datasets without forget…