About me

I am a researcher at OpenAI. Previously, I received my Ph.D. in Computer Science from UC Berkeley, where I was fortunate to be advised by Jelani Nelson and Avishay Tal. Before that, I did my undergrad in Yao Class, Tsinghua University. Even before that, in high school, I was a competitive programmer.

During my PhD, I spent several years trying to understand the role of memory in computation from a TCS standpoint. This includes fun and specific questions like:

• How many memory accesses are needed to decide whether n numbers are distinct?
• How to approximate the median when you can only look at each datapoint once?
• Can you solve a set of equations when you can only look at each equation once? Twice? $O(1)$ times?

It is amazing how these very specific and simple-looking questions can lead to very deep lines of research and many beautiful ideas.

As I was pivoting toward LLMs, I wrote the following here in summer 2025:

More recently, my interests have shifted toward the LLM revolution, including reasoning and self-improvement. In summer 2025, I interned at Microsoft Research, mentored by Janardhan Kulkarni on LLM reasoning and self-improvement. Nowadays, with only noisy human data and compute, LLMs are able to solve competitive-level math and algorithm problems. It is foreseeable that with new training recipes and more engineering, data, architecture, and algorithmic innovation, they will be able to solve not only all the specific problems above, but also the grand open problems that I have no clue how one might attack:

• Is P separable from L? (Can every time-efficient algorithm also be made very memory-efficient?)
• Is RL equal to L? (Is randomness useless for very memory-efficient algorithms?)

LLMs are going to fundamentally change how theoreticians work.

Less than a year later, this has already become reality. See our podcast on the refutation of the Erdos unit distance conjecture. A new era for theoretical research is already here.

For me, doing theory has been an enjoyable journey, and I have worked with very kind and inspiring professors that I am always grateful to.

• Prof. Ryan Williams
• Prof. Zhihao Gavin Tang
• Prof. Hu Fu
• Prof. Mikkel Thorup
• Prof. Ran Duan