I am a Research Fellow at the Kempner Institute at Harvard.
I am working on problems across the language modeling stack, spanning problems from data selection and creation to optimization to architectures to reinforcement learning. I value simple, principled, and scalable algorithms. Previously, my PhD thesis focused on understanding and improving algorithms for offline reinforcement learning.
Prior to coming to Harvard, I did my PhD at NYU advised by Joan Bruna and supported by an NDSEG fellowship. During that time, I interned at Google Brain, MSR, and FAIR. And before that, I undergraduated at Yale.
If you are interested in collaborating, please reach out via email!