Justin Y. Chen

Welcome!

I am a PhD student in my final year at MIT. I study computer science in the Theory of Computation Group. I am very happy to be advised by Piotr Indyk.

I think about problems at the intersection of algorithm design and machine learning. Recently, I have been crafting algorithms which (1) interact with powerful but untrustworthy AI models (learning-augmented algorithms and LLM evaluation), (2) are stable to small changes in their inputs (differential privacy and replicability), and (3) efficiently learn with as little data and compute as possible.

During my PhD, I have been fortunate to be supported by the NSF Graduate Research Fellowship and MathWorks Engineering Fellowship and to work at Google Research and AWS. I was an undergrad at Stanford University and had the great pleasure of working with Greg Valiant and Peter Bailis. It all started in Hanover, New Hampshire with Chris Polashenski at the Cold Regions Research and Engineering Laboratory.

Feel free to reach out to me at {first 4 letters of first name}{first letter of last name}@mit.edu.

News

Sep 2025 Quanta Magazine wrote about our work on “Evaluating the World Model Implicit in a Generative Model”.

Aug 2025: Google Research highlighted our work “Scalable Private Partition Selection via Adaptive Weighting” in a blog post. This was a very interesting project I worked on as a Student Researcher at Google Research.

Apr 2025: The Wall Street Journal wrote about our work on “Evaluating the World Model Implicit in a Generative Model”.