Thomas Brox

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

Overcoming Challenges of Long-Horizon Prediction in Driving World Models

When and How Does CLIP Enable Domain and Compositional Generalization?

Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach

Leveraging Knowledge Graphs to harvest a high-quality dataset for efficient CLIP model training

Selective Concept Bottleneck Models Without Predefined Concepts

What Matters for In-Context Learning: A Balancing Act of Look-up and In-Weight Learning