Subject identity variance dominates frozen representations in three EEG foundation models by 13-89x over null, and erasing the linear subject axis improves label decoding where within-subject label variation exists.
Franco, Michael P
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
Channel adaptation for EEG foundation models is architecture- and regime-dependent, with flexible models showing negative transfer risks during fine-tuning and small models outperforming larger ones on most tasks.
LRP on EEG transformers reveals Clever Hans artifacts in motor imagery tasks and a recurring central electrode cluster as a candidate sensorimotor signature of arousal.
Pretrained scalp-EEG foundation models can be transferred to ECoG via adapters and fine-tuning to match or exceed subject-specific baselines on regression tasks while requiring far less per-patient data.
A survey organizes deep learning techniques including feature alignment, adversarial learning, feature disentanglement, and contrastive learning to tackle cross-subject generalization in EEG decoding while formalizing evaluation protocols.
citing papers explorer
-
The Identity Trap in EEG Foundation Models: A Diagnostic Audit
Subject identity variance dominates frozen representations in three EEG foundation models by 13-89x over null, and erasing the linear subject axis improves label decoding where within-subject label variation exists.
-
Channel Adaptation for EEG Foundation Models: A Systematic Benchmark Across Architectures, Tasks, and Training Regimes
Channel adaptation for EEG foundation models is architecture- and regime-dependent, with flexible models showing negative transfer risks during fine-tuning and small models outperforming larger ones on most tasks.
-
From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP
LRP on EEG transformers reveals Clever Hans artifacts in motor imagery tasks and a recurring central electrode cluster as a candidate sensorimotor signature of arousal.
-
CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
Pretrained scalp-EEG foundation models can be transferred to ECoG via adapters and fine-tuning to match or exceed subject-specific baselines on regression tasks while requiring far less per-patient data.
-
Cross-Subject Generalization for EEG Decoding: A Survey of Deep Learning Methods
A survey organizes deep learning techniques including feature alignment, adversarial learning, feature disentanglement, and contrastive learning to tackle cross-subject generalization in EEG decoding while formalizing evaluation protocols.