Dresden 2026 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

DY: Fachverband Dynamik und Statistische Physik

DY 58: Focus Session: Physics of AI – Part II (joint session SOE/DY)

DY 58.6: Hauptvortrag

Freitag, 13. März 2026, 11:15–11:45, GÖR/0226

Creativity in generative AI — •matthieu wyart — JHU & EPFL

Is AI creative? Generative AI such as chatGPT or diffusion models can create new texts or images from a finite training set of examples. I will argue that AI can achieve this magical by learning how compose observed low-level elements into a new whole. I will discuss the type of correlations the model can exploit to do so, how many data are needed for that, and how it relates to a hierarchical construction of latent variables. The analysis is based on the introduction of synthetic languages, and comparison with experiments performed on modern AI architectures trained on real text and images.