Publications

my publications sorted by year (* indicates equal contribution)

2026

  1. ICLR
    ADM-v2: Pursuing Full-Horizon Roll-out in Dynamics Models for Offline Policy Learning and Evaluation
    Haoxin Lin, Siyuan Xiao, Yi-Chen Li, Zhilong Zhang, Yihao Sun, Chengxing Jia, and Yang Yu
    In Proceedings of the 14th International Conference on Learning Representations, 2026
    Link Code
  2. NN
    Any-step Dynamics Model Improves Future Predictions for Offline Reinforcement Learning via Hierarchical Roll-out
    Haoxin Lin, Yihao Sun, Yi-Chen Li, Zhilong Zhang, Chengxing Jia, and Yang Yu
    Neural Networks, 2026
    Link
  3. ICML
    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, and Yang Yu
    In Proceedings of the 43rd International Conference on Machine Learning, 2026
    Link Code
  4. ICML
    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, and Yang Yu
    In Proceedings of the 43rd International Conference on Machine Learning, 2026
    Link

2025

  1. ICLR
    Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
    Haoxin Lin, Yu-Yan Xu, Yihao Sun, Zhilong Zhang, Yi-Chen Li, Chengxing Jia, Junyin Ye, Jiaji Zhang, and Yang Yu
    In Proceedings of the 13th International Conference on Learning Representations, 2025
    Link Blog Code
  2. NeurIPS EWM
    WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making
    Zhilong Zhang, Ruifeng Chen, Junyin Ye, Yihao Sun, Haoxiang Ren, Xinghao Du, Pengyuan Wang, Jing-Cheng Pang, Kaiyuan Li, Tian-Shuo Liu, Haoxin Lin, Yang Yu, and Zhi-Hua Zhou
    In NeurIPS 2025 Workshop on Embodied World Models for Decision Making, 2025
    Link

2024

  1. AAAI
    Episodic Return Decomposition by Difference of Implicitly Assigned Sub-trajectory Reward
    Haoxin Lin, Hongqiu Wu, Jiaji Zhang, Yihao Sun, Junyin Ye, and Yang Yu
    In Proceedings of the 38th Annual AAAI Conference on Artificial Intelligence, 2024
    Link Code

2023

  1. ECAI
    Model-based Reinforcement Learning with Multi-step Plan Value Estimation
    Haoxin Lin*, Yihao Sun*, Jiaji Zhang, and Yang Yu
    In Proceedings of the 26th European Conference on Artificial Intelligence, 2023
    Link Code
  2. ICML
    Model-Bellman Inconsistency for Model-based Offline Reinforcement Learning
    Yihao Sun*, Jiaji Zhang*, Chengxing Jia, Haoxin Lin, Junyin Ye, and Yang Yu
    In Proceedings of the 40th International Conference on Machine Learning, 2023
    Link Code
  3. FCN
    Learning Fair and Efficient Multiple Access Schemes with Decomposed MADDPG
    Zhaoyang Liu, Haoxin Lin, Xijun Wang, Jie Gong, and Xiang Chen
    In 2023 International Conference on Future Communications and Networks, 2023
    Link