3 papers
cs.AI2026
Flattening the Connectome Spectrum: A Spectral Filter for FC Induces a Pretraining Target for fMRI Encoders
Giovanni Marraffini, Victoria Shevchenko, Carlo Alberto Barbano +1
Self-supervised pretraining reshaped prediction in language and vision, and brain foundation models (BFMs) inherited its promise. Representations learned from large unlabelled corp…
cs.LG2026
CoCoT-EEG: Contrastive-Pretrained Multiscale Convolutional Transformer for EEG Decoding
Gabriel Mahuas, Victoria Shevchenko, Ugo Tanielian +2
Self-supervised pretrained foundation models (FM) have shown early promise for non-invasive electroencephalogram (EEG) decoding applications. Many recent large-scale models converg…
q-bio.NC2026
The Variance Brain Foundation Models Forgot: Third-Order Statistics Predict Cognition Where Billion-Parameter Models Fail
Giovanni Marraffini, Gabriel Mahuas, Trinidad Borrell +2
Brain foundation models (BFMs) are self-supervised Transformers pretrained on fMRI data. We posit that these models should capture each subject's cognitive performance from their f…