avatar

Chenxiao Yang
杨 晨晓

PhD Student
Toyota Technological Institute at Chicago (TTIC)
chenxiao [at] ttic (dot) edu


🤗 Hi! I am Chenxiao, a PhD student at Toyota Technological Insitute at Chicago, an independent philanthropically endowed computer science research institute located on the University of Chicago campus. I am fortunate to be advised by Zhiyuan Li and to collaborate closely with David McAllester and Nathan Srebro. Previously, I was a research intern at Amazon Web Services, mentored by David Wipf. I received both my M.S. and B.S. degrees from Shanghai Jiao Tong University, where I worked with Junchi Yan. For more details, see CV. My primary research interests include:

1️⃣ Reasoning & Planning with LLMs: I study how today’s large language models work and where they fundamentally fall short. In doing so, I seek to develop practical methods to push them toward tackling harder tasks — faster, cheaper, and with results we can verify.

2️⃣ Machine Learning Theory: Theoretically, I explore how training dynamics and architectural inductive biases synergize to produce generalizable solutions. I am especially interested in out-of-distribution settings, which are common in graph learning and increasingly critical in the LLM era.

3️⃣ Learning on Graphs: I investigate surprising phenomena in graph learning, uncover their underlying causes and mechanisms, and use these insights to develop simple yet powerful graph-based models that may challenge mainstream beliefs.

Although I’m not actively researching them, I maintain side interests in theoretical computer science, causal inference, generative models (e.g. diffusion models), and machine-learning applications for scientific discovery (e.g. biology) and data mining (e.g. recommender systems).

Recent News

Selected Publications

Full list of publications can be found in Google Scholar

  1. ICML'25
    ✏️ PENCIL: Long Thoughts with Short Memory
    Chenxiao Yang, Nathan Srebro, David McAllester, Zhiyuan Li
    International Conference on Machine Learning (ICML), 2025.
    PDF Code Poster Slides Talk Blog 博客

  2. ICML'24
    How Graph Neural Networks Learn: Lessons from Training Dynamics
    Chenxiao Yang, Qitian Wu, David Wipf, Ruoyu Sun, Junchi Yan
    International Conference on Machine Learning (ICML), 2024.
    PDF Code Poster

  3. ICLR'23
    Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs
    Chenxiao Yang, Qitian Wu, Jiahua Wang, Junchi Yan
    International Conference on Learning Representations (ICLR), 2023.
    PDF Code Poster 视频 博客

Services

Misc

In my free time I enjoy hiking, traveling, swimming, photography, and experimenting with AI-generated art. I also like to dabble in psychology and philosophy.

Feel free to leave anonymous feedback about me or my research here!