Morten Mørup

This paper introduces SCENE, a probabilistic model for embedding cells and genes in scRNA-seq data, achieving state-of-the-art performance and interpretable visualization.

This paper introduces a mixture modeling approach to analyze brain phase coherence networks from fMRI data, identifying recurring synchronized activity states across cognitive tasks without task labels.

This paper introduces EnCAR, a method for estimating asymmetric fiber orientation distribution functions in diffusion MRI, showing improved performance in complex regions.

This study shows that automatic deep learning models for mouse sleep scoring struggle to generalize across labs due to signal variability and label noise, and proposes four robust models trained on diverse data.

This study examines neural responses to repeated sounds in individuals with 22q11.2 deletion syndrome, finding reduced adaptation but intact prediction, linked to negative symptom severity.