Dresden 2026 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
SOE: Fachverband Physik sozio-ökonomischer Systeme
SOE 14: Focus Session: Physics of AI I (joint session SOE/DY)
Donnerstag, 12. März 2026, 09:30–11:15, GÖR/0226
The focus session is organized by Claudius Gros (Goethe-Universität Franfurt), Moritz Helias (Forschungszentrum Jülich), Peter Sollich (Georg-August-Universität Göttingen)
This focus session brings together experts in the field of physics-inspired theory of machine learning and artificial intelligence, who aim to supplement the engineering-driven success of AI by a principled theory of neural information processing. Contributions will address how statistical and dynamical perspectives explain learning in modern AI systems and how these insights support interpretability as well as prediction of performance, generalization, and the required resources.
![]() |
09:30 | SOE 14.1 | Hauptvortrag: Generative AI and diffusion models: a statistical physics approach — •Giulio Biroli |
![]() |
10:00 | SOE 14.2 | Statistical Physics of Classifier-free Diffusion Guidance — •Enrico Ventura, Beatrice Achilli, Carlo Lucibello, and Luca Ambrogioni |
![]() |
10:15 | SOE 14.3 | Fundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines — •Alberto Fachechi, Elena Agliari, Miriam Aquaro, Anthony Coolen, and Menno Mulder |
![]() |
10:30 | SOE 14.4 | Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias? — •Tom Jacobs, Chao Zhou, and Rebekka Burkholz |
![]() |
10:45 | SOE 14.5 | Generalization performance of narrow one-hidden layer networks in the teacher-student setting — Rodrigo Pérez Ortiz, •Gibbs Nwemadji, Jean Barbier, Federica Gerace, Alessandro Ingrosso, Clarissa Lauditi, and Enrico Malatesta |
![]() |
11:00 | SOE 14.6 | Testing generalization through tiny task switching frameworks — •Daniel Henrik Nevermann and Claudius Gros |

