I am a PhD student in the Brain & Cognitive Sciences (BCS) department at MIT, where I work with Roger Levy, Ev Fedorenko, and many other wonderful mentors and collaborators. I am grateful for funding support from the NSF GRFP and an MIT Presidential Fellowship. My research sits at the interface of cognitive science and AI, where I work on building robust and pragmatic AI systems that can solve problems spanning natural language, programming, and mathematics. Towards this goal, I jointly leverage LLMs alongside tools from Bayesian machine learning and symbolic AI. See ProbSem and LINC for early outputs of this research program, the latter of which won an outstanding paper award at EMNLP '23. Prior to starting my PhD, I studied Computational Neuroscience and Complex Systems at the University of Michigan, and worked for several years on machine learning applications to neuroscience, including publications in Nature, PNAS, and NeurIPS.
Open Source I care about open source and allocate a portion of my time towards community contributions. These have previously included the development and evaluation of code models with the Star Coder project by Hugging Face and Service Now, the first implementation of CFG-guided text generation for the Outlines library by .txt, and contributions to AI for mathematics with Project Numina. I am also developing the Decoding library, a framework that makes it easy to design and implement custom LLM search and inference algorithms, built from a set of pure composable building blocks.
June 2024: Joined Project Numina as a contributor, facilitating the release of the models, datasets, and code used to win the first AIMO progress prize.