Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/5ICML 2026Poster· Applications / Robotics

ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation

Nan Tang · Jing-Cheng Pang · Guanlin Li · Chao Qian · Yang Yu

多模态OpenReview

作者位次 #6/6ICML 2026Poster· Reinforcement Learning / Inverse

Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Value Flow Mechanism

Tian Xu · Chenyang Wang · Xiaochen Zhai · Ziniu Li · Yi-Chen Li · Yang Yu

安全可解释性强化学习与后训练OpenReview

作者位次 #7/7ICML 2026Poster· Reinforcement Learning / Multi-agent

Learning Disentangled Multi-Agent World Model for Decentralized Control

Di Xue · Jing Jiang · Shaowei Zhang · Wenhao Guo · lei yuan · Zongzhang Zhang · Yang Yu

智能体与工具强化学习与后训练OpenReview

作者位次 #9/9ICML 2026Poster

Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation

Zhichao Wu · Junyin Ye · Zhilong Zhang · Yihao Sun · Haoxin Lin · Jiaheng Luo · Haoxiang Ren · lei yuan · Yang Yu

OpenReview

作者位次 #7/7ICML 2026Poster· Reinforcement Learning / Multi-agent

Towards Complete Multi-Agent Coordination Policy Learning via Denoising Maximum Entropy Optimization

Guanghao Li · lei yuan · Ruiqi Xue · Hengchang Zhang · Jianhong Wang · Yi-Chen Li · Yang Yu

智能体与工具强化学习与后训练OpenReview

作者位次 #3/3ICML 2026Poster· Reinforcement Learning / Multi-agent

Decentralized and Disentangled Task–Role Representation Learning for Generalizable Offline Multi-Agent Meta Reinforcement Learning

lei yuan · Ruiqi Xue · Yang Yu

智能体与工具可解释性强化学习与后训练OpenReview

作者位次 #7/7ICML 2026Poster· Reinforcement Learning / Inverse

Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning

Tian Xu · Zexuan Chen · Zhilong Zhang · Yi-Chen Li · Chenyang Wang · lei yuan · Yang Yu

安全强化学习与后训练效率与系统OpenReview

作者位次 #7/7ICML 2026Poster

Clipping Low-Probability Tokens in SFT Yields a Generalizable Initialization for RL

Tian-Shuo Liu · Chengxing Jia · Haoyu Liu · Pengyuan Wang · Shiyuan Zhang · Jie Fu · Yang Yu

强化学习与后训练理论与学习动力学OpenReview

作者位次 #9/9ICML 2026Poster

Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models

Zhilong Zhang · Haoxiang Ren · Yihao Sun · Yifei Sheng · Haonan Wang · Zhichao Wu · Haoxin Lin · Pierre-Luc Bacon · Yang Yu

多模态强化学习与后训练OpenReview

作者位次 #5/5ICML 2026Poster· Reinforcement Learning / Multi-agent

Offline Multi-agent Continual Cooperation via Skill Partition and Reuse

Yuchen Xiao · lei yuan · Ruiqi Xue · Tieyue Yin · Yang Yu

智能体与工具强化学习与后训练OpenReview

Yang Yu

获取完整研究档案

联系方式

2026 顶会论文

ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation

Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Value Flow Mechanism

Learning Disentangled Multi-Agent World Model for Decentralized Control

Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation

Towards Complete Multi-Agent Coordination Policy Learning via Denoising Maximum Entropy Optimization

Decentralized and Disentangled Task–Role Representation Learning for Generalizable Offline Multi-Agent Meta Reinforcement Learning

Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning

Clipping Low-Probability Tokens in SFT Yields a Generalizable Initialization for RL

Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models

Offline Multi-agent Continual Cooperation via Skill Partition and Reuse

常见合作者