01.05.2026
MCML at AISTATS 2026
Ten Accepted Papers (8 Main, and 2 Workshops)
29th International Conference on Artificial Intelligence and Statistics, Tangier, Morocco, May 02-05, 2026
We are happy to announce that MCML researchers have contributed a total of 10 papers to AISTATS 2026: 8 Main, and 2 Workshop papers. Congrats to our researchers!
Main Track (8 papers)
The Riemannian Geometry associated to Gradient Flows of Linear Convolutional Networks.
AISTATS 2026 - 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. URL
Efficient Learning of Stationary Diffusions with Stein-type Discrepancies.
AISTATS 2026 - 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. URL
On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors.
AISTATS 2026 - 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. Spotlight Presentation. URL
Orthogonal Representation Learning for Estimating Causal Quantities.
AISTATS 2026 - 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. Oral Presentation. URL
Conformal Prediction in Hierarchical Classification with Constrained Representation Complexity.
AISTATS 2026 - 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. URL
Semi-Implicit Variational Inference via Kernelized Path Gradient Descent.
AISTATS 2026 - 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. URL
Standard Acquisition Is Sufficient for Asynchronous Bayesian Optimization.
AISTATS 2026 - 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. URL GitHub
Rethinking Intrinsic Dimension Estimation in Neural Representations.
AISTATS 2026 - 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. URL
Workshops (2 papers)
Towards E-Value Based Stopping Rules for Bayesian Deep Ensembles.
OPTIMAL @AISTATS 2026 - Workshop on Optimisation and Post-Bayesian Inference in Machine Learning at the 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. To be published. Preprint available. arXiv GitHub
Guiding Posterior Exploration with Optimizer-Derived Geometry.
OPTIMAL @AISTATS 2026 - Workshop on Optimisation and Post-Bayesian Inference in Machine Learning at the 29th International Conference on Artificial Intelligence and Statistics. Tangier, Morocco, May 02-05, 2026. To be published. Preprint available. arXiv GitHub
Related
17.11.2026
Enkelejda Kasneci: The Real Value of AI in Education Is More Time for Humans
Enkelejda Kasneci explores how AI can provide personalized learning support while keeping human interaction and student agency at the center.
12.11.2026
One Toolbox for Many Kinds of Uncertainty
MCML researchers introduce probly, a unified Python package for uncertainty-aware machine learning, presented orally at NeurIPS 2026.
09.11.2026
Outstanding Paper Award at EMNLP 2026 for Work on Accent Bias in Audio Language Models
A paper co-authored by MCML PI Valentin Hofmann on accent bias in audio language models won an Outstanding Paper Award at EMNLP 2026.