张泽楷 (Zekai Zhang)

About Me

I am a third-year PhD student in EECS at the University of Michigan, advised by Prof. Qing Qu. Before this, I received my bachelor’s degree from the Department of Automation, Tsinghua University.

Research

My research focuses on first principles for deep neural networks, such as representations and low-dimensional structures. Recently, I have been interested in representation learning in diffusion models and multimodal models.

Representation learning would be the brain science for AI.

News

• May 2026
  Happy to announce that I will be interning at TikTok Seattle this summer!
• Jan 2026
  One paper accepted at ICLR 2026.

  Generalization of Diffusion Models Arises with a Balanced Representation Space, with an oral talk at DeepMath.
• Oct 2025
  Two papers accepted at NeurIPS 2025.

  A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling
• May 2025
  Top Reviewer award at ICML 2025.
• May 2024
  Awarded the MICDE Fellowship.
• Sep 2023
  Awarded the National Scholarship of China.