6 papers · 1 filter
HaWMPO: Hallucination-Aware World Model-based Policy Optimization for Generalist Robot Policy
Zengjue Chen, Peidong Liu, Jiawei Li +1
Generalist robot policies have demonstrated strong generalization across robotic manipulation tasks, yet their success rates remain limited in com- plex long-horizon scenarios. Rec…
RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution
Tao Wang, Wei Wang, Jianhui Wang +4
Cloud-side inference expands the computational resources available to imitation-learning policies, but communication and inference latencies create a mismatch between prediction an…
Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation
He Kong, Zengjue Chen, Qi Wang +6
Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models. However, existing post-traini…
Policy and World Modeling Co-Training for Language Agents
Ning Lu, Baijiong Lin, Shengcai Liu +9
Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do…
RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
Yixiu Mao, Yun Qu, Qi Wang +2
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, its effe…
World Action Models are Zero-shot Policies
Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng +33
State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce Drea…