← Search

Dominik J. Mühlematter

2 accepted papers

2026

Making Foundation Models Probabilistic via Singular Value Ensembles

ICML 2026poster

Foundation models have become a dominant paradigm in machine learning, achieving remarkable performance across diverse tasks through large-scale pretraining. However, these models often yield overconfident, uncalibrated predictions. The standard approach to quantifying epistemic uncertainty, trainin…

Cited by 0SourceScholar
2026

UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations

ICML 2026poster

Forecasting urban phenomena such as housing prices and public health indicators requires the effective integration of various geospatial data. Current methods primarily utilize task-specific models, while recent generic models for spatial representations often support only limited modalities and lac…

Cited by 2SourceScholar