About me

I am a fifth-year PhD student in Statistics at UC Berkeley, where I work on theoretical machine learning and statistics with Song Mei and Peter Bartlett. Before Berkeley, I received a B.S. in Statistics from Peking University, where I work with Cheng Zhang.

My work focuses on the statistical foundations and algorithms for AI. I use and extend tools from statistical learning theory, high-dimensional statistics, and optimization to study the statistical foundations of architectures, algorithms and phenomena in modern AI (e.g., Transformers, in-context learning, scaling laws, contrastive learning and multimodal generative AI), and to build mathematically motivated algorithms for AI alignment (e.g., LLM unlearning).

I am also broadly interested in LLM reasoning, high-dimensional statistics, and statistical inference. In my spare time, I enjoy basketball, hiking and traveling.