Fengzhuo Zhang

About Me

I am a Postdoctoral Fellow at the Center for Algorithms, Data, and Market Design at Yale University, where I am fortunate to be mentored by Professors Dirk Bergemann and Zhuoran Yang. I received my Ph.D. in Electrical and Computer Engineering from the National University of Singapore in 2025 under the guidance of Professors Vincent Y. F. Tan and Lin Zhao. Prior to that, I received my B.Eng. in Electronic Engineering from Tsinghua University in 2020, where I had the privilege of working with Professor Yuan Shen.

My research interests lie in the statistical and optimization theory of foundation models. My recent work studies the optimization and training dynamics of language models, statistical models of In-Context Learning and Chain-of-Thought reasoning, and economic models of LLM services grounded in these optimization and statistical characterizations.

Selected Publications

1. Relative Generalization Invariance of LLM Pretraining. F. Zhang^*,†, S. Wang^*, S. Li^*, T. Ruan, J. He, I. Tsang, T. Pang, C. Du, T. Zhang, Z. Yang. Under review. paper
2. Why Muon Outperforms Adam: A Curvature Perspective. S. Wang^*, F. Zhang^*,†, J. Li, D. Bergemann, Z. Yang. Advances in Neural Information Processing Systems (NeurIPS), 2026. paper
3. Muon Outperforms Adam in Tail-End Associative Memory Learning. S. Wang^*, F. Zhang^*,†, J. Li^*, C. Du, C. Du, T. Pang, Z. Yang, M. Hong, V. Y. F. Tan. International Conference on Learning Representations (ICLR), 2026. paper
4. Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion. F. Zhang, Z. Yang, D. Bergemann. ACM Conference on Economics and Computation (EC), 2026.
   Under review at Operations Research. paper
5. Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods. X. Hu, F. Zhang, S. Chen, Z. Yang. Journal of Machine Learning Research (JMLR), 2026, to appear. paper
6. What and How Does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization. Y. Zhang^*, F. Zhang^*, Z. Yang, Z. Wang. International Conference on Artificial Intelligence and Statistics (AISTATS), 2025. paper

Full publication list →

News

• Jul. 2026Gave a talk at the Shanghai Innovation Institute on “Why Muon Outperforms Adam: A Curvature Perspective.”
• 2026“Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods” is to appear in JMLR.
• 2026“Supervised Fine-Tuning vs. In-Context Learning” appeared at ACM EC.
• Feb. 2026Gave a talk at Nexus for IntelligeCE on the slash pattern in attention and RoPE.
• Jan. 2026Joined Yale University as a Postdoctoral Fellow at CADMY.
• Jun. 2025Completed a Ph.D. in Electrical and Computer Engineering at NUS.

Appointments and Education