杜兴豪 Xinghao Du M.Sc. Student, LAMDA Group School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University , Nanjing 210023, China Supervisor: Prof. Yang Yu Email: duxh@lamda.nju.edu.cn Laboratory: A201, Shaoyifu Building, Nanjing University Xianlin Campus

Biography

Currently, I am an M.Sc. student at the School of Artificial Intelligence , Nanjing University, and a member of the LAMDA Group , led by Prof. Zhi-Hua Zhou . I am supervised by Prof. Yang Yu .

I received my B.Sc. degree in Artificial Intelligence from the School of Artificial Intelligence , Nanjing University in June 2024. In September 2024, I continued my study at Nanjing University as an M.Sc. student.

Research Interests

My research interests include Reinforcement Learning and its applications. Recently, I am interested in:

• Reinforcement Learning: especially on Offline Reinforcement Learning;

• Embodied Intelligence: including robot learning, world models, and multimodal foundation models such as VLMs and VLAs.

Publications

Journal Papers

• Single-cell omics data-driven decoding of tumor clonal evolution through reinforcement learning
  Qiushun He*, Zhilong Zhang*, Yuanmei Wang*, Xinghao Du, Chenxi Xie, Yueyuxiao Yang, Huanming Yang, Yang Yu, Meng Yang.
  Genome Medicine, 18:79, 2026.

Conference Papers

• Hierarchical Value-Decomposed Offline Reinforcement Learning for Whole-Body Control
  Zhilong Zhang*, Yunpeng Mei*, Xinghao Du*, Hongjie Cao*, Haonan Wang, Pengyuan Min, Chenyu Wang, Pengfei Chen, Chenbo Xin, Yijie Wang, Wenyu Luo, Yihao Sun, Yidi Wang, Lei Yuan, Gang Wang, Yang Yu.
  In Proceedings of the 14th International Conference on Learning Representations (ICLR'26), 2026.

• Improving Reward Model Generalization from Adversarial Process Enhanced Preferences
  Zhilong Zhang*, Tian Xu*, Xinghao Du*, Xingchen Cao, Yihao Sun, Yang Yu.
  In Proceedings of the 42nd International Conference on Machine Learning (ICML'25), 2025.

Workshop Papers

• Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation
  Zhilong Zhang*, Wenyu Luo*, Haonan Wang*, Yifei Sheng*, Yidi Wang, Hanyuan Guo, Haoxiang Ren, Xinghao Du, Yuhan Che, Tongtong Cao, Lei Yuan, Yang Yu.
  IROS 2026 Workshop on Physical World Models for Scaling Embodied AI (PWMS), 2026.

• WHALE: Towards Generalizable and Scalable World Models for Embodied Decision-making
  Zhilong Zhang*, Ruifeng Chen*, Junyin Ye*, Yang Yu*, Yihao Sun, Haoxiang Ren, Xinghao Du, Pengyuan Wang, Jingcheng Pang, Kaiyuan Li, Tianshuo Liu, Haoxin Lin, Zhi-Hua Zhou.
  NeurIPS 2025 Workshop on Embodied World Models for Decision Making (EWM), 2025.

* Equal contribution.

Correspondence

Email: duxh@lamda.nju.edu.cn

Laboratory:
A201, Shaoyifu Building, Xianlin Campus of Nanjing University

Address:
National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China
(南京市栖霞区仙林大道163号, 南京大学仙林校区603信箱, 软件新技术国家重点实验室, 210023.)