Machine learning theory has long focused on classical supervised learning settings, where a model is trained on input–label pairs drawn from a well-defined data distribution, with the aim of achieving low test error on such distribution. Despite remarkable advances in such settings, recent breakthroughs in generative AI have transformed our understanding of generalization, revealing phenomena such as emergent capabilities and in-context learning, which lie beyond the scope of existing theoretical frameworks. These empirical developments call for new theoretical paradigms, fostering closer interactions between theoreticians and practitioners to address the distinctive challenges posed by generative models.
The purpose of this workshop is to bring together diverse theory-oriented communities to articulate and synthesize core principles underlying modern generative AI, and to outline the central challenges in advancing our scientific understanding.
Date: December 7th, 2025
Location: Copenhagen, Denmark
09:00--09:45: Plenary speaker 1
09:45--10:15: 2x15 min contributed talks
10:15--11:15: Break/Poster Session 1
11:15--12:00: Plenary speaker 2
(12:00--13:30) Lunch break
13:30--14:15: Plenary speaker 3
14:15--15:00: 3x15 min contributed talks
15:00--16:00: Break/Poster Session 2
16:00--16:45: Plenary speaker 4
16:45--17:30: Plenary speaker 5
17:30--18:30: Panel discussion & Closing Remarks
SPIGM@NeurIPS: We welcome all authors of accepted papers at the SPIGM@NeurIPS workshop who are unable to travel to the US to join us and present their work during the poster sessions.
Contact: prigm-eurips-2025@googlegroups.com