Chenxiao Yang
杨 晨晓

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 Nathan Srebro. Previously, I was a research intern at Amazon Web Services, mentored by David Wipf. I received 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 Next-Generation Generative Models: I am interested in analyzing the strengths and limitations of current generative models (e.g. LLMs, diffusion models) from a theoretical perspective. In doing so, I explore simple and novel approaches or fundamental principles that overcome these limitations, enabling models to reason and generate more efficiently and effectively, and work universally across domains such as natural langauge, math, coding, science, etc.

2️⃣ Theory of Modern Learning Paradigm: I am also curious about various modern learning paradigms that emerge in the era of LLMs and how they should be positioned in the landscape of machine learning theory to enrich our understanding. I am especially interested in understanding expressivity of various models and how they develop out-of-distribution generlization capabilities through large-scale training.

3️⃣ Learning on Graphs: I develop new algorithms or models that can better handle combinatorial structures and complex topologies such as graphs and sequences with some global constraints, which are prevelant in domains such as biology.

I maintain side interests in theoretical computer science, causal inference, reinforcement learning, and machine-learning applications for scientific discovery.

Recent News

• [2025.06] PENCIL won best poster award at Midwest Machine Learning Symposium 2025.
• [2025.05] I will be giving talks at FLaNN (May 26), ASAP (May 28) and LOGS (May 31) seminars.
• [2025.05] Two papers were accepted in ICML 2025! One about the theoretical limitation of CoT and a new LLM reasoning paradigm, another about a principled graph transformer.

Selected Publications

Full list of publications can be found in Google Scholar

Teaching

• Teaching Assistant, TTIC 31020 Introduction to Machine Learning, Fall 2025

Services

• International Conference on Machine Learning (ICML) 2022-
• Advances in Neural Information Processing Systems (NeurIPS) 2022-
• International Conference on Learning Representations (ICLR) 2024-
• International Conference on Artificial Intelligence and Statistics (AISTATS) 2025-

Misc

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