8 NeurIPS 2026 papers accepted, including oral position paper

Enlarge

Researchers from the Chair of Artificial Intelligence and Machine Learning have had 8 of their papers (6 first name) accepted into the 41st Conference on Neural Information Processing Systems (NeurIPS 2026).

Among them, an oral position paper, one of only 9 in the whole conference.

Position Track:

1. The Aleatoric-Epistemic Dichotomy of Uncertainty is Meaningful and Indispensable for Machine Learning. Yusuf Sale, Nikita Kotelevskii, Maxim Panov, Eyke Hüllermeier (Oral)

Main Track:

1. Proxy-Based Approximation of Shapley and Banzhaf Interactions. Santo M. A. R. Thies, Hubert Baniecki, R. Teal Witter, Eyke Hüllermeier, Maximilian Muschalik, Fabian Fumagalli. [arxiv]
2. OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators. Joshua Stiller, Santo MAR Thies, Felix Czaja, Eyke Hüllermeier. [arxiv]
3. Conformal Prediction for Time-Dependent PDEs. Joshua Stiller, Annika Schneider, Eyke Hüllermeier.
4. Deferred Aggregation in Hierarchical Bayesian Optimization. Valentin Margraf, Jonas Hanselle, Julian Rodemann, Marcel Wever, Sebastian Josef Vollmer, Eyke Hüllermeier.

Evaluations and Datasets Track:

1. probly: Uncertainty-Aware Machine Learning. Paul Hofman, Clemens Damke, Timo Löhr, Santo M. A. R. Thies, Alireza Javanmardi, Valentin Margraf, Jakub Paplhám, Yusuf Sale, Eyke Hüllermeier, and Maximilian Muschalik. (Oral)
2. Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning. Jakub Paplhám, Willem Waegeman, Eyke Hüllermeier, Vojtěch Franc. [arxiv]
3. Feedback Forensics: A Toolkit to Measure AI Personality. Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier, Robert D. Mullins. [arxiv]