NERVE uses network-aware bilinear tokenization of FC matrix patches in a masked autoencoder to learn more stable and cross-cohort transferable representations than standard region-centric or graph-based approaches.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Network-Aware Bilinear Tokenization for Brain Functional Connectivity Representation Learning
NERVE uses network-aware bilinear tokenization of FC matrix patches in a masked autoencoder to learn more stable and cross-cohort transferable representations than standard region-centric or graph-based approaches.