Zihao Wang
I am a Ph.D. candidate at Stanford Mathematics, where I am extremely fortunate to be advised by Andrea Montanari. I also work closely with Percy Liang. During the 2026 summer I interned at the Flatiron Institute in New York, working with Joan Bruna, Alberto Bietti, and Denny Wu.
Previously, I received my B.S. in Mathematics from Peking University in 2024 and visited Princeton in 2023. I was fortunate to be advised by Jason D. Lee and Lei Wu for my undergraduate research.
01
Research
I am interested in AI. In particular, I want to enable AI to make creative contributions to science—for instance, discovering new statistical algorithms for complex experimental data, and developing a scientific understanding of AI systems themselves.
I also want to understand the societal and economic impact of AI and what it means for humanity—where the unique value of human intelligence lies, and how we should interact and co-evolve with this new form of intelligence.
02
Publications
* indicates equal contribution or alphabetical author order. Representative papers are highlighted.
One-Sided Verification Under Limited Expert Review
Investigating Human–AI Discrepancies via Multiple-Solution Problems
Algorithmic Separation between Constant-Depth and Logarithmic-Depth Neural Networks
Phase Transitions for Feature Learning in Neural Networks
Neural Networks Learn Generic Multi-Index Models near Information-Theoretic Limit
UQ: Assessing Language Models on Unsolved Questions
Learning Hierarchical Polynomials of Multiple Nonlinear Features
The Local Landscape of Phase Retrieval Under Limited Samples
Learning Hierarchical Polynomials with Three-Layer Neural Networks
Theoretical Analysis of the Inductive Biases in Deep Convolutional Networks
03
Awards
- Weiming Scholar, Peking University
- Francis Robbins Upton Fellowship (declined), Princeton University
04
Talks
- Learning theory workshop, Tsinghua University
- Spring retreat, Department of Statistics, Stanford
- ML theory reading group, Stanford
- ML theory reading group, Simons Institute, Berkeley
- MaD seminar, New York University
- CCM seminar, Flatiron Institute
- ML theory reading group, Wharton, UPenn
- ML seminar, Peking University
- ML theory reading group, Tsinghua University
05
Other
I love travelling and want to explore places off the beaten path. One of my favorite books is The Art of Travel by Alain de Botton. One of my favorite movies is Nomadland by Chloé Zhao.
I am proud to be born and raised in Qingdao, a coastal city where I grew up just a stone's throw from the sea.