I believe that artificial intelligence will be society's most powerful lever for scientific discovery and technological change. I've mainly worked on LLM benchmarking, the science of deep learning, climate science, and biophysics. 

 

Here are some of my recent research projects:

• HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics (ICLR 2025)

• Training Dynamics of Convolutional Neural Networks for Learning the Derivative Operator (NeurIPS 2024 SciForDL Workshop)

• Humanity's Last Exam (Featured in The New York Times and Reuters)

• A Comparative Analysis of Tornadic Debris and Debris Fallout Signatures from the 10 – 11 December 2021 and 28 – 29 May 2019 Tornadoes (41st Conference on Environmental Information Processing Technologies)

• Polarimetric Characteristics of Tornadic Debris Fallout during the 28 May 2019 Lawrence/Kansas City, Kansas, Tornado (2020 AMS Annual Meeting)