My research is at the intersection of machine learning and the physical sciences. I came to this from astrophysics - fluid flows around supernovae, neutron star mergers, neutrino physics, cosmic rays - and that background shapes how I think about what ML needs to do to work for fundamental physics problems.

I develop new ML methods — foundation models, PDE surrogates, mechanistic interpretability — and apply them to fundamental physics problems ranging from continuum dynamics to astrophysics.

I currently lead efforts on foundation models for scientific data at Cambridge and within the Polymathic AI collaboration.

I am open to supervising PhD and masters students. If you're interested in working with me, feel free to get in touch.