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 shaping the future of software, but it also risks making software more vulnerable. My research aims not only to address this AI safety challenge, but also to leverage AI to make software systems safer AND more capable than ever before. To realize this goal, I develop formal methods to improve the trustworthiness of learning-enabled systems and study AI-assisted 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.

Selected work:

• Evaluating Text-to-SQL Evaluation with Formal Verification [ICLR’26]
• Cubing for Tuning [AAAI’26]
• Marabou 2.0: A Versatile Formal Analyzer of Neural Networks [CAV’24]
• Integrating Large Language Models in Automated Program Verification [ICLR’24]
• Efficient Neural Network Analysis with Sum-of-Infeasibilities [TACAS’22]
• All publications