Research

Publications and Preprints

(\(\dagger\) indicates the research group leader and advising.)

Reinforcement Learning

• Adversarially robust RL

  • On the Tension Between Optimality and Adversarial Robustness in Policy Optimization
    Haoran Li, Jiayu Lv, Congying Han, Zicheng Zhang, Anqi Li, Yan Liu, Tiande Guo, Nan Jiang.
    (ICLR 2026) 14th International Conference on Learning Representations.

  • Towards Optimal Adversarial Robust Reinforcement Learning with Infinity Measurement Error
    Haoran Li, Zicheng Zhang, Wang Luo, Congying Han, Jiayu Lv, Tiande Guo, Yudong Hu.
    Under major revision at JMLR.

  • Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error
    Haoran Li, Zicheng Zhang, Wang Luo, Congying Han, Yudong Hu, Tiande Guo, Shichen Liao.
    (ICML 2024 Oral, < 1.5%) 41st International Conference on Machine Learning.

  • ARPO: Optimal Robust Policy Optimization Models from Intrinsic State-Adversarial Markov Decision Process
    Jiayu Lv, Haoran Li\(^\dagger\), Congying Han, Tiande Guo.
    (JORSC 2026) Journal of the Operations Research Society of China.

• Game theory/Multi-agent RL

  • A-PSRO: A Unified Strategy Learning Method with Advantage Metric for Normal-form Games
    Yudong Hu, Haoran Li, Congying Han, Tiande Guo, Mingqiang Li, Bonan Li.
    (ICML 2025) 42nd International Conference on Machine Learning.

  • Modeling Opponent Learning in Multiagent Repeated Games
    Yudong Hu, Congying Han, Haoran Li, Tiande Guo.
    (Appl Intell 2023) Applied Intelligence.

• Offline model-based RL

  • Mitigating Distribution Shift in Model-based Offline RL via Shifts-aware Reward Learning
    Wang Luo, Haoran Li\(^\dagger\), Zicheng Zhang, Congying Han, Chi Zhou, Jiayu Lv, Tiande Guo.
    Preprint.

  • Dual Alignment Maximin Optimization for Offline Model-based RL
    Chi Zhou, Wang Luo, Haoran Li\(^\dagger\), Congying Han, Tiande Guo, Zicheng Zhang.
    Preprint.

Machine Learning for Combinatorial Optimization

• Purity Law for Neural Routing Problem Solvers with Enhanced Generalizability
  Wenzhao Liu, Haoran Li\(^\dagger\), Congying Han, Zicheng Zhang, Anqi Li, Tiande Guo.
  (NeurIPS 2025) 39th Annual Conference on Neural Information Processing Systems.

• Optimal Pivot Path of the Simplex Method for Linear Programming based on Reinforcement Learning
  Anqi Li, Tiande Guo, Congying Han, Bonan Li, Haoran Li.
  (Sci China Math 2024) Science China Mathematics.

• Fusion of Multi-level Information: Solve Large-scale Traveling Salesman Problem with an Efficient Framework
  Wenzhao Liu, Congying Han, Tiande Guo, Haoran Li\(^\dagger\), Zicheng Zhang.
  (ICONIP 2024) 31st International Conference on Neural Information Processing.

• Neural Farsighted Simplex Framework for Internalizing Long-horizon Fusion Information
  Anqi Li, Congying Han, Tiande Guo, Haoran Li, Zicheng Zhang, Wenzhao Liu, Ning Li.
  Preprint.

• Harnessing Strategic Foresight to Mitigate Myopia in Evolutionary Meta-heuristics
  Anqi Li, Congying Han, Tiande Guo, Haoran Li, Bonan Li.
  Preprint.

VLM/LLM Training

• The Primacy of Magnitude in Low-Rank Adaptation
  Zicheng Zhang, Haoran Li, Yifeng Zhang, Guoqiang Gong, Jiaxing Wang, Pengzhang Liu, Qixia Jiang, Junxing Hu.
  (NeurIPS 2025 Spotlight, < 3%) 39th Annual Conference on Neural Information Processing Systems.

• TANDEM: Bi-Level Data Mixture Optimization with Twin Networks
  Jiaxing Wang, Deping Xiang, Jin Xu, Mingyang Yi, Guoqiang Gong, Zicheng Zhang, Haoran Li, Pengzhang Liu, Zhen Chen, Ke Zhang, Ju Fan, Qixia Jiang.
  (NeurIPS 2025) 39th Annual Conference on Neural Information Processing Systems.