Program & Schedule

Session 1 (Chair: Siu Lun Chau, Shireen Kudukkil Manchingal)

08:45-09:00   Opening Remarks

    Organising Committee

09:00-09:30   Invited talk: Eyke Hüllermeier 

• The Aleatoric-Epistemic Dichotomy of Uncertainty Quantification in Machine Learning: Challenges, Doubts, and Opportunities

09:30-10:00   Invited talk: Fanny Yang

• Robust distributional generalization with imperfect knowledge of the robust risk

10:00-10:30 Oral presentations #1 (12min + 3minQ&A each)

• Maxitive Donsker–Varadhan Formulation for Possibilistic Variational Inference

  • Jasraj Singh, Shelvia Wongso, Jeremie Houssineau, Badr-Eddine Chérief-Abdellatif

• Uncertainty-aware diffusion models for probabilistic regression

  • Carlo Kneissl, Christopher Bülte, Philipp Scholl, Gitta Kutyniok

10:30-11:00   Coffee break

Session 2 (Chair: Shireen Kudukkil Manchingal)

11:00-11:30 Invited talk: Fabio Cuzzolin

• Towards an epistemic generative AI

11:30-12:30 Poster session #1

12:30-13:30 Lunch break

Session 3 (Chair: Krikamol Muandet)

13:30-14:00 Oral presentations #2 (12min + 3minQ&A each)

• A Formal Assessment of Uncertainty Measures in Regression 

  • Christopher Bülte, Yusuf Sale, Timo Löhr, Paul Hofman, Gitta Kutyniok, Eyke Hüllermeier 

• Entropy Is Not Enough: Uncertainty Quantification for LLMs fails under Aleatoric Uncertainty

  • Tim Tomov, Dominik Fuchsgruber, Tom Wollschläger, Stephan Günnemann

14:00-15:00 Poster session #2

15:00-15:30 Coffee break

Session 4 (Chair: Michele Caprio)

15:30-16:00   Invited talk: Ryan Martin

• Imprecision is Imperative for Valid Uncertainty Quantification in Machine Learning

16:00-17:00   Panel discussion: Is probability sufficient for the next generation epistemic AI?

• Fabio Cuzzolin, Eyke Hüllermier, Ryan Martin, Fanny Yang, Jason Konek, Gert de Cooman

17:00-17:15  Closing remarks

    Organizing Committee