My current work focuses on understanding fundamental phenomena in artificial intelligence. My approach, which I call 'Phenomenology of Deep Learning', draws from my background in particle physics phenomenology to combine rigorous theoretical analysis with empirical evidence. For instance, see [here] for our work on emergence and scaling laws and [here] for our work on double descent and online/offline correspondence in similarity learning. 

Previously, I explored the construction of models to explain small- and large-scale phenomena in the universe. I worked on the interplay between particle physics theory and cosmology, learning from the early universe how to build and interpret our models of particle physics. See [here] for all publications.