Marcel van Gerven

Subspace Node Pruning: Revealing Structured Importance via Orthogonal Subspace Transformations

GRAM: Spatial general-purpose audio representations for real-world applications

Probabilistic Forecasting via Autoregressive Flow Matching

Decorrelation Speeds Up Vision Transformers

WavJEPA: Semantic learning unlocks robust audio foundation models for raw waveforms

Effective Learning with Node Perturbation in Multi-Layer Neural Networks

Subspace Node Pruning