01About
I am a first-year Ph.D. student at MIT CSAIL, advised by Profs. Constantinos Daskalakis and Russ Tedrake. My research interests lie broadly in the theory of machine learning. More specifically, I am interested in the theory of post training in the context of diffusion models (and their applications to robotics), continual learning in language models, and other questions related to generative modeling. Previously, I worked on various questions related to the theory of low-rank fine tuning in neural networks, distributed optimization and learning in multiagent systems, and strategic interactions in LLMs.
During summer 2026, I am a research intern at Microsoft Research New England, advised by Dylan Foster.
Previously, I received an A.B. in Computer Science and Mathematics and an S.M. in Computer Science from Harvard University in May 2025. During my undergraduate education, I was fortunate to work on the theory of low-rank fine-tuning with SGD (advised by Prof. Sitan Chen), and various problems in distributed / multi-agent optimization (advised by Profs. Stephanie Gil and Angelia Nedich).
02Publications
A selection of work below. For the full list, see my Google Scholar page.
-
Low-rank fine-tuning lies between lazy training and feature
learning
Conference on Learning Theory (COLT) 2025
-
Learning From Synthetic Labs: Language Models as Auction Participants
ArXiv Preprint 2025
-
Projected push-pull for distributed constrained optimization
over time-varying directed graphs
American Control Conference (ACC) 2024
-
Learning trust over directed graphs in multiagent systems
Learning for Dynamics and Control Conference (L4DC) 2023
03Industry Experience
-
Summer 2026
Research Intern
Microsoft Research - Cambridge, MA
-
Summer 2022
Data Science Intern
Trendyol Group - Istanbul, Turkey
04Teaching
During my time at Harvard, I had the privilege of serving the CS and math community as a course assistant for:
-
CS 121
Introduction to Theoretical Computer Science
Theory of computation — circuits, Turing machines, computability, complexity, reductions, and randomized computation. Taught by Boaz Barak.
-
Math 25b
Theoretical Linear Algebra & Real Analysis II
Rigorous single- and multivariable real analysis, metric space topology, and basic Fourier analysis. Taught by Wes Cain.
-
Math 25a
Theoretical Linear Algebra & Real Analysis I
A rigorous introduction to linear algebra based on the wonderful Linear Algebra Done Right. Taught by Wes Cain.
-
ES 150
Probability with Engineering Applications
Fundamental probability concepts and their applications to engineering problems. Taught by Yue M. Lu.
05Writing
Some expository notes and essays
-
Stochastic
Localization and Sampling via Time Reversal
2026
An expository class project (MIT 18.676) connecting sampling, stochastic localization, and filtering through time-reversals of SDEs, with an eye toward diffusion-based generative modeling.
-
Learning in Neural Networks: Lazy training, Feature Learning, and Fine-Tuning
2025
My undergraduate thesis including exposition on learning in neural networks and original research on learning dynamics of low-rank fine tuning.
-
Leap
Complexity: How SGD Exploits Hierarchical Structure to Learn
Efficiently
Dec 2023
An expository class project (Harvard CS 224) on how stochastic gradient descent can go beyond the kernel regime to perform hierarchical feature learning.