3 papers
cs.LG2026
Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data
Dominik Schnaus, Thomas Dagès, Daniel Cremers +2
Multimodal representations enable zero-shot classification and retrieval, but aligning independently trained models usually requires large amounts of paired data. Yet, the Platonic…
cs.CV2025
It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Data
Dominik Schnaus, Nikita Araslanov, Daniel Cremers
The platonic representation hypothesis suggests that vision and language embeddings become more homogeneous as model and dataset sizes increase. In particular, pairwise distances w…
cs.LG2023
Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
Dominik Schnaus, Jongseok Lee, Daniel Cremers +1
In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks. The key idea is to exploit scalable and stru…