Hello!

I am a final year Computer Science Ph.D. student at the University of Pennsylvania advised by Prof. Rajeev Alur and Prof. Eric Wong. This fall, I’ll be starting my postdoc at UT Austin’s Center for Generative AI, hosted by Prof. Adam Klivans.

My goal is to make ML systems safe and interpretable using formal methods, control theory, and optimization! I am broadly interested in:

  • Making LLMs better at logical reasoning
  • Training models that are interpretable by design
  • Developing simple yet useful explainability techniques
  • Establishing formal guarantees for ML systems
  • Linear algebra and big matrices