About me!
Hi! I am a second year PhD student at the University of Texas at Austin. I am advised by Dr. Swarat Chaudhuri in the Trustworthy & Intelligent Systems Lab. I conduct research in neurosymbolic techniques for automated mathematical reasoning and program synthesis.
Research
Through my second year as a graduate student at UT Austin, I have been involved in two projects broadly falling under the umbrella term “AI for Mathematics.” I organized a team of university students to produce a new formal competition maths benchmark for evaluating the next generation of mathematical reasoning automation. PutnamBench was accepted at NeurIPS 2024 and recognized at the ICML 2024 AI for Math Workshop via the Best Paper Award. I also contributed to COPRA, an agentic LLM-based approach for formal theorem-proving.
While in undergrad, I conducted research with the Rutgers Automated Reasoning Lab, being advised by He Zhu. I worked on using differentiable programming for invariant synthesis for program verification. Before conducting computer science research, I was involved in research in theoretical maths. I participated in an NSF REU at the College of William & Mary under the advisement of Charles R. Johnson, and working with Greyson Wesley and Zach Zhao. We studied some topics regarding eigenvalue assignment of certain graphs, and, among other things, proved several results for $k-$NIM trees, including characterization and enumeration. We submitted a paper following the conclusion of the REU based on the results we showed. The second was in person at San Diego State University, under the advisement of Chris O’Neill. We studied symmetric numerical semigroups, and more particularly properties of unimaximal faces of the Kunz Cone. We gave a characterization of the facets of these unimaximal faces and constructed some extremal examples of numerical semigroups on these faces.