Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics
Sam Gijsen, MichaÅ Åukomski, Marc-André Schulz +1
Flow matching and diffusion models enable conditional generation across domains ranging from images to proteins, with recent extensions to out-of-distribution contexts. Yet generat…
cs.LG2026
Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model
Sam Gijsen, Marc-Andre Schulz, Kerstin Ritter
The development of foundation models for functional magnetic resonance imaging (fMRI) time series holds significant promise for predicting phenotypes related to disease and cogniti…