I am a PhD student in Computer and Information Science at the University of Pennsylvania, where I am fortunate to be co-advised by Osbert Bastani and Dinesh Jayaraman. My research interests include improving the reasoning abilities of large multimodal models in domains like visual reasoning, robotics, programming, and math.
Previously, I graduated with a bachelor's degree from Massachusetts Institute of Technology, where I double-majored in computer science and mathematics. There, I worked with Armando Solar-Lezama and Omar Costilla-Reyes on neurosymbolic program synthesis and Stefanie Shattuck-Hufnagel and Jeung-Yoon Elizabeth Choi on acoustic cue detection. I also spent a summer at Imperial College, London working with Cristopher Salvi. You can find out more about my coursework and teaching here.
I am a member of trustML@Penn, the ASSET Center, and the Perception, Action, & Learning (PennPAL) Group at the GRASP Laboratory. If you are an undergraduate or MS student interested in working with me, please fill out the PennPAL collaboration research group form here - I (and other PennPAL PhD students) regularly monitor responses to the form and will reach out to you if there is an opening. For all other collaborations or inquiries, please email me - I'd love to hear from you!
Updates
Selected Works
BrowserArena: Evaluating LLM Agents on Real-World Web Navigation Tasks
An arena-style benchmark for evaluating web agents on realistic web navigation tasks.
Effective Reinforcement Learning for Reasoning in Language Models
Pre-emptive sampling and gradient filtering for improving GRPO performance.