Simon Schrodi

Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer

What Drives Compositional Generalization in Visual Generative Models?

Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models

When and How Does CLIP Enable Domain and Compositional Generalization?

Selective Concept Bottleneck Models Without Predefined Concepts