I am a physicist and researcher working at the intersection of theoretical neuroscience and machine learning.

My work focuses on developing theoretical frameworks that explain how neural networks—both artificial and biological—learn, represent, and memorize complex structures through their high-dimensional dynamics and geometry.

Drawing on methods from statistical physics, I derive analytical theories of learning dynamics, sparse coding, and neural representations.

I have presented my research at leading conferences such as COSYNE and ICML, and mentored projects at the Brains, Minds & Machines course at MBL.