Generative AI, Diffusion Models and Statistical Physics
| When |
Nov 17, 2025
from 11:00 to 12:00 |
|---|---|
| Where | Salle Condorcet |
| Contact Name | David Carpentier |
| Attendees |
Giulio Biroli |
| Add event to calendar |
vCal
iCal
|
Generative AI represents a groundbreaking development within the broader “Machine Learning Revolution,” significantly influencing technology, science, and society. In this colloquium, I will discuss remarkable connections between generative AI, in particular diffusion models, and statistical physics. Diffusion models are the state of the art to generate images, videos, and sounds. They are very fascinating algorithms for physicists, as they are very much connected to concepts from stochastic thermodynamics, particularly time-reversed Langevin dynamics. These diffusion models start from a simple white noise input and make it evolve through a Langevin process to generate complex outputs such as images, videos, and sounds. I will show that statistical physics provides principles and methods to characterise this generation process. Specifically, I will discuss how phenomena such as the transition from memorization to generalization and the emergence of features can be understood through the lens of symmetry breaking, phase transitions, disordered systems, and dynamics in complex energy landscapes.