Zhiyuan Li (李志远)

prof_pic.jpg

Office: TTIC 508

I am a tenure-track assistant professor at Toyota Technological Institute at Chicago (TTIC) and an affiliated faculty of Computer Science at the University of Chicago. I am also a visiting faculty at Google Research. Before joining TTIC, I was a postdoctoral fellow in Computer Science Department at Stanford University, working with Tengyu Ma. I received my PhD from the Computer Science Department at Princeton University in 2022, where I was advised by Sanjeev Arora. I did my undergraduate study at Yao Class, Tsinghua University.

I am broadly interested in machine learning theory, including optimization in deep learning, reasoning capabilities of Large Language Models (LLMs), modern paradigm of generalization in machine learning (overparameterization, out-of-domain generalization) and its connection to the implicit bias of optimization algorithms.

News

Jan 26, 2026 2 papers accepted by ICLR 2026!
Jan 22, 2026 1 paper accepted by AISTATS 2026!
Jan 12, 2026 Co-organizing the Latent & Implicit Thinking – Going Beyond CoT Reasoning workshop at ICLR 2026!
Sep 18, 2025 1 paper accepted by NeurIPS 2025!
Jun 23, 2025 Excited to co-organize and participate in Midwest Machine Learning Symposium at Uchicago!

Selected and Recent publications

  1. On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond
    Chenxiao Yang, Cai Zhou, David Wipf, and Zhiyuan Li
    In The Fourteenth International Conference on Learning Representations, ICLR 2026
    arXiv Bib
  2. Structured Preconditioners in Adaptive Optimization: A Unified Analysis
    Shuo Xie, Tianhao Wang, Sashank Reddi, Sanjiv Kumar, and Zhiyuan Li
    In Proceedings of the 42nd International Conference on Machine Learning, ICML 2025
    arXiv Bib
  3. PENCIL: Long Thoughts with Short Memory
    Chenxiao Yang, Nathan Srebro, David McAllester, and Zhiyuan Li
    In Proceedings of the 42nd International Conference on Machine Learning, ICML 2025
    arXiv Bib
  4. Weak-to-Strong Generalization Even in Random Feature Networks, Provably
    Marko Medvedev, Kaifeng Lyu, Dingli Yu, Sanjeev Arora, Zhiyuan Li, and Nathan Srebro
    In Proceedings of the 42nd International Conference on Machine Learning, ICML 2025
    arXiv Bib
  5. Non-Asymptotic Length Generalization
    Thomas Chen, Tengyu Ma, and Zhiyuan Li
    In Proceedings of the 42nd International Conference on Machine Learning, ICML 2025
    arXiv Bib
  6. Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity
    Shuo Xie, Mohamad Amin Mohamadi, and Zhiyuan Li
    In The Thirteenth International Conference on Learning Representations, ICLR 2025
    Spotlight arXiv Bib
  7. Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
    Zhiyuan Li, Hong Liu, Denny Zhou, and Tengyu Ma
    In The Twelfth International Conference on Learning Representations, ICLR 2024
    arXiv Bib
  8. How Does Sharpness-Aware Minimization Minimize Sharpness?
    Kaiyue Wen, Tengyu Ma, and Zhiyuan Li
    In The Eleventh International Conference on Learning Representations, ICLR 2023
    arXiv Bib
  9. What Happens after SGD Reaches Zero Loss?--A Mathematical Framework
    Zhiyuan Li, Tianhao Wang, and Sanjeev Arora
    In The Tenth International Conference on Learning Representations, ICLR 2022
    Spotlight arXiv Bib
  10. Why Are Convolutional Nets More Sample-Efficient Than Fully-Connected Nets?
    Zhiyuan Li, Yi Zhang, and Sanjeev Arora
    In The Ninth International Conference on Learning Representations, ICLR 2021
    Oral arXiv Bib