Alessandro Favero

Hey there! I’m a final-year PhD student at EPFL, where I’m advised by Matthieu Wyart and Pascal Frossard. During my PhD, I interned as an applied scientist at Amazon’s AWS AI Labs with Stefano Soatto’s team.

I work on the physics of machine learning and intelligence, investigating the fundamental principles that underlie learning in artificial intelligence systems. What makes natural data learnable? How is the structure of the world represented within AI models? How does performance scale with both model and data size? Right now, I study compositional aspects of diffusion and deep generative models across vision and language modalities. Additionally, I work on post-training modeling strategies to edit and disentangle neural representations, improving alignment and enabling model merging.

Before my PhD, I completed a joint Master’s degree in theoretical physics from Sorbonne Université, Politecnico di Torino, SISSA, and ICTP.