I am broadly interested in the intersection of physics and machine learning. My work encompasses LLMs for time series, integrating ML into thermodynamic processes for time-series and PDE modeling, ML chemical potentials, and inverse problems.

Biography

I am a postdoctoral researcher investigating the intersection of Physics, Chemistry, and AI with Michael Mahoney and Benjamin Erichson. I have a joint appointment at the Berkeley Statistics department, Lawrence Berkeley National Lab, and the International Computer Science Institute. I received my Physics PhD from Stanford in 2023 under the mentorship of Phil Bucksbaum and Ryan Coffee where I researched excited state quantum molecular dynamics through ultrafast gas-phase diffraction. For my dissertation, I applied theoretical physics, statistics, and fundamental machine learning techniques to invert the measured diffraction patterns for molecular frame structure probability distributions, addressing a 50 year-old inverse problem. During the summer of 2019 I interned at Google X as an AI Research Fellow where I worked in the blushift team using adversarial examples to probe fundamental properties between disparate neural network architectures.

I received an Honors B.Sc from the University of Michigan, majoring in Physics and Math. During this time I researched High Energy Particle Physics at CERN with Bing Zhou. My research focused on the discovery of the Higgs Boson and measuring its spin.