Sitan Chen
Assistant Professor of Computer Science
Kempner Associate Faculty
Contact Information
Subjects I Teach:
- Algorithms and Data Structures
- Theory of Machine Learning
- Quantum Learning Theory
Areas I Research:
About
Sitan Chen is an Assistant Professor of Computer Science at Harvard SEAS, where he is a member of the Theory of Computation and the Harvard Quantum Initiative, and an associate faculty at the Kempner Institute. Previously, he was an NSF math postdoc at UC Berkeley, after completing his PhD in EECS at MIT in 2021. His work has been recognized with an NSF CAREER award, an ICML Outstanding Paper Award, and the Harvard Dean’s Competitive Fund for Promising Scholarship.
Research Focus
Chen’s group studies how intelligence can emerge from iterative refinement: systems that begin in uncertainty and gradually sharpen their predictions by revising and steering their outputs. His research develops the mathematical foundations for modern generative AI—especially diffusion and flow-based models—and turns them into faster, more reliable algorithms for sampling from rich, high-dimensional distributions.
A central goal is to rethink how AI systems learn from and simulate complex objects, from images and language to models of the physical universe. In collaboration with researchers at the Kempner Institute, his group has pursued the design of language models that can reason, self-correct, and generate flexibly, rather than one token at a time. He also uses insights from the foundations of ML to understand inverse problems in the sciences, including how quantum computers can help reveal the structure of physical systems.