RE-CONFIRM shows that standard fine-tuning of foundation models fails to recover known regional hubs in neurological disorders, while Hub-LoRA recovers them and outperforms custom models.
Rethinking stability for attribution-based expla- nations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.NC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Foundation models for discovering robust biomarkers of neurological disorders from dynamic functional connectivity
RE-CONFIRM shows that standard fine-tuning of foundation models fails to recover known regional hubs in neurological disorders, while Hub-LoRA recovers them and outperforms custom models.