Haoran Li 李浩冉

Ph.D. candidate University of Chinese Academy of Sciences, Operations Research Email: haoranl@illinois.edu Google Scholar | Github | X

I am a final-year Ph.D. candidate at the University of Chinese Academy of Sciences (UCAS), advised by Prof. Tiande Guo and Prof. Congying Han. I also work closely with Dr. Zicheng Zhang.

Currently, I am a visiting Ph.D. Student at the University of Illinois Urbana-Champaign (UIUC), advised by Prof. Nan Jiang.

Before beginning my graduate studies, I earned my B.S. in Mathematics from the University of Science and Technology of China (USTC).

Research Interests

My research focuses on trustworthy reinforcement learning across theory, algorithms, and applications. I am dedicated to developing theoretically grounded algorithms that can effectively guide practical scenarios, aiming to bridge the gap between theoretical guarantees and empirical performance.

Broadly, I am also interested in the interplay between machine learning and optimization, with a particular focus on policy optimization, machine learning for combinatorial optimization (ML4CO), training of large language models (LLMs) and vision-language models (VLMs).

Selected Honors and Awards

• National Scholarship, Ministry of Education, China (2025)

• President Scholarship, Academy of Mathematics and Systems Science, Chinese Academy of Sciences (2024)

• Loo-Keng Hua Scholarship, Academy of Mathematics and Systems Science, Chinese Academy of Sciences (2021)

Selected Publications and Preprints

Reinforcement Learning

• 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.

• 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.

• 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.

Machine Learning for Combinatorial Optimization

• Purity Law for Neural Routing Problem Solvers with Enhanced Generalizability
  Wenzhao Liu, Haoran Li, 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.

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.

Service

• Reviewer: NeurIPS, ICLR, ICML