5 papers
On the modality gap and the contrastive loss in multi-modal representation learning
Fabian Mager, Hiba Nassar, Lars Kai Hansen
We study the modality gap in CLIP-style dual-encoder contrastive learning, where image and text embeddings remain misaligned despite being trained in a shared space. We argue that…
Improving Relative Representations with Learned Anchors and Whitened Inner Products
Oscar Thorsted Svendsen, Nikolaj Holst Jakobsen, Fabian Mager +1
Independently trained neural models typically converge to incompatible latent representations, creating a fundamental barrier to highly modular AI systems. While Relative Represent…
On What We Can Learn from Low-Resolution Data
Theresa Dahl Frehr, Niels Henrik Pontoppidan, Hiba Nassar +1
Artificial intelligence systems typically rely on large, centrally collected datasets, a premise that does not hold in many real-world domains such as healthcare and public institu…
Spline Based Methods for Functional Data on Multivariate Domains
Rani Basna, Hiba Nassar, Krzysztof Podgórski
Functional data analysis is typically performed in two steps: first, functionally representing discrete observations, and then applying functional methods to the so-represented dat…
Efficient spline orthogonal basis for representation of density functions
Jana Burkotová, Ivana Pavlů, Hiba Nassar +2
Probability density functions form a specific class of functional data objects with intrinsic properties of scale invariance and relative scale characterized by the unit integral c…