Alice Bizeul — accepted AI-conference papers

2025

Cross-Entropy Is All You Need To Invert the Data Generating Process

Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E Vogt, Randall Balestriero, Wieland Brendel +1

ICLR 2025oral

Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neural analogy-making and the linear representation hypothesis, suggest that supervised models can learn interpretable factor…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

Identifiability Results for Multimodal Contrastive Learning

Imant Daunhawer, Alice Bizeul, Emanuele Palumbo, Alexander Marx, Julia E Vogt

ICLR 2023poster

Contrastive learning is a cornerstone underlying recent progress in multi-view and multimodal learning, e.g., in representation learning with image/caption pairs. While its effectiveness is not yet fully understood, a line of recent work reveals that contrastive learning can invert the data generati…

Cited by 48 Source ↗PDF ↗code ↗Scholar ↗