Scientific Breakthrough Reveals Why Generative AI Learns So Effectively
A study led by Tony Bonnaire (IAS, CNRS & Université Paris-Saclay) in collaboration with Raphaël Urfin and Giulio Biroli (ENS Paris, CNRS & PSL) and Marc Mézard (Bocconi University) sheds unprecedented light on a central question in generative AI research: how diffusion models—the key technology behind modern generative AI—manage to generalize efficiently before memorizing the training data.










