I am an Assistant Professor of Computer Science at Amherst College. I am also affiliated with Broadcom and the Manning College of Information and Computer Sciences at UMass Amherst.
AI is reshaping the future of software, but it also risks making our software more vulnerable. Addressing existing AI safety challenges is essential; at the same time, I believe AI presents a unique opportunity to make software systems SAFER and more capable than ever before. My research aims to advance both goals. Concretely, I am developing automated reasoning techniques to improve the trustworthiness of AI-enabled systems and designing protocols that combine inductive and logical reasoning to enable scalable automated reasoning.
I got my PhD at Stanford University in 2024, advised by Clark Barrett. Before that, I graduated with BS in Mathematics and Philosophy from Davidson College.
If you are an undergraduate or graduate student interested in working with me, please reach out!
Selected work:
AR for AI
- Evaluating Text-to-SQL Evaluation with Formal Verification [ICLR’26]
- Marabou 2.0: A Versatile Formal Analyzer of Neural Networks [CAV’24]
- Efficient Neural Network Analysis with Sum-of-Infeasibilities [TACAS’22]
AI for AR
- Cubing for Tuning [AAAI’26]
- Lemur: Integrating Large Language Models in Automated Program Verification [ICLR’24]
- Lightweight Online Learning for Sets of Related Problems in Automated Reasoning [FMCAD’23]
AI-AR co-design
- Viverra: Text-to-Code with Guarantees [NeurIPS’26]