I’m a Ph.D. candidate from Gaoling School of Artificial Intelligence (GSAI), Renmin University of China, advised by Prof. Liu.

I received my bachelor’s and master’s degrees from School of Information, Renmin University of China when I was advised by Prof. Zhao from DW&BI Lab.

My current research interests mainly include the mechanism analysis of Large Language Models (LLMs).

You can find more information about me in my CV.

Publications

Beyond the Black Box: Theory and Mechanism of Large Language Models

Zeyu Gan, Ruifeng Ren, Wei Yao, Xiaolin Hu, Gengze Xu, Chen Qian, Huayi Tang, Zixuan Gong, Xinhao Yao, Pengwei Tang, Zhenxing Dou, Yong Liu. Beyond the Black Box: Theory and Mechanism of Large Language Models. arXiv preprint arXiv:2601.02907, 2026.

Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents

Guoqing Wang, Sunhao Dai, Guangze Ye, Zeyu Gan, Wei Yao, Yong Deng, Xiaofeng Wu, Zhenzhe Ying. Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents. arXiv preprint arXiv:2510.14967, 2025.

CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning

Zeyu Gan, Hao Yi, Yong Liu. CoT-Space: A Theoretical Framework for Internal Slow-Thinking via Reinforcement Learning. arXiv preprint arXiv:2509.04027, 2025.

Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning

Zeyu Gan, Yun Liao, Yong Liu. Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning. In The 42nd International Conference on Machine Learning (ICML), 2025.

Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective

Zeyu Gan, Yong Liu. Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective. In The Thirteenth International Conference on Learning Representations (ICLR), 2025.

Towards a Theoretical Understanding of Semi-Supervised Learning Under Class Distribution Mismatch

Pan Du, Suyun Zhao, Puhui Tan, Zisen Sheng, Zeyu Gan, Hong Chen, Cuiping Li. Towards a Theoretical Understanding of Semi-Supervised Learning Under Class Distribution Mismatch. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 47, 6 (June 2025), 4853-4868.

Superclass Learning with Representation Enhancement

Zeyu Gan, Suyun Zhao, Jinlong Kang, Liyuan Shang, Hong Chen, Cuiping Li. Superclass Learning With Representation Enhancement. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 24060-24069, 2023.

Contact Information

If you are interested in my works, please feel free to contact me for discussions by Email.