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.
Brain foundation models: A survey on advancements in neural signal processing and brain discovery
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
SCOPE uses cohort-level external supervision, confidence-aware pseudo-labels, and a lightweight prototype-conditioned adapter (ProAdapter) to adapt frozen EEG foundation models in label-limited settings, reporting consistent gains across 50 experimental configurations.
CodeBrain introduces a decoupled TFDual-Tokenizer and multi-scale EEGSSM architecture for an EEG foundation model pretrained on a large corpus, claiming strong generalization across eight downstream tasks and ten datasets.
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.
-
SCOPE: Structured Prototype-Guided Adaptation for EEG Foundation Models with Limited Labels
SCOPE uses cohort-level external supervision, confidence-aware pseudo-labels, and a lightweight prototype-conditioned adapter (ProAdapter) to adapt frozen EEG foundation models in label-limited settings, reporting consistent gains across 50 experimental configurations.
-
CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model
CodeBrain introduces a decoupled TFDual-Tokenizer and multi-scale EEGSSM architecture for an EEG foundation model pretrained on a large corpus, claiming strong generalization across eight downstream tasks and ten datasets.