Pascal Mettes

The Human Brain as a Dynamic Mixture of Expert Models in Video Understanding

Compositional Entailment Learning for Hyperbolic Vision-Language Models

Union-over-Intersections: Object Detection beyond Winner-Takes-All

Distortion-free and GPU-compatible Tree Embeddings in Hyperbolic Space

BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulation

Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space

Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectors

Binary Hyperbolic Embeddings

Exemplar-free Continual Representation Learning with Symmetric Distillation

Large Language Models Are Natural Video Popularity Predictors