I’m a fourth-year CS student at Peking University, working with Prof. Yisen Wang, Prof. Lin Yang, and Prof. Amy Zhang. My research goal is to design more powerful and efficient algorithms in reinforcement learning and to provide theoretical understanding for existing representation learning paradigms. My latest CV is here.

Email: kaiwenhu [at] stu (dot) pku (dot) edu (dot) cn

Research Interests

• Representation Learning: Revisiting the existing deep learning (e.g., self-supervised learning) paradigms and uncovering their underlying mechanisms theoretically.

• Reinforcement Learning: Improving the sample efficiency of multiple settings with guarantees of robustness.

News

• 2025.03: I have accepted the PhD offer from UC Berkeley EECS. Many thanks!
• 2025.01: Our paper on contrastive learning theory is accepted at ICLR 2025!
• 2024.09: Our paper on equivariant self-supervised learning theory is accepted at NeurIPS 2024!

Publications

Projection Head is Secretly an Information Bottleneck
Zhuo Ouyang*, Kaiwen Hu*, Qi Zhang, Yifei Wang, Yisen Wang
In ICLR 2025.
PDF | Code

Understanding the Role of Equivariance in Self-supervised Learning
Yifei Wang*, Kaiwen Hu*, Sharut Gupta, Ziyu Ye, Yisen Wang, Stefanie Jegelka
In NeurIPS 2024.
PDF | Code