Cross-Cohort Spectral-Temporal Dissociation in Frozen EEG Foundation-Model Representations

arXiv:2607.24834 · q-bio.NC, cs.AI, cs.ET, cs.LG · Submitted 2026-08-19 · Read on arXiv

Marzieh Zare

q-bio.NC, cs.AI, cs.ET, cs.LG

Submitted: 2026-08-19

Updated: 2026-08-20

Code: https://github.com/MarziehzZare/eeg-fm-criticality-probe

Terminology

• alpha — 21× in this paper · explained in 1 episode
• Embeddings — 19× in this paper · explained in 2 episodes
• Foundation Model — 17× in this paper · explained in 3 episodes
• Foundation Models — 13× in this paper · explained in 7 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Residualization — 5× in this paper · explained in 2 episodes
• Temporal Correlations — 5× in this paper · explained in 2 episodes
• Decode — 4× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Non-stationarity — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Foundation Models (FMs) — 2× in this paper · explained in 2 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Zero-Shot Transfer — 2× in this paper · explained in 4 episodes
• AUROC — 1× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Algorithmic Stability — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Exchangeability — 1× in this paper · explained in 2 episodes
• In International Conference on Learning Representations — 1× in this paper
• Mechanistic interpretability — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Time Series Forecasting — 1× in this paper · explained in 3 episodes

Sources

• A spectral audit framework reveals task-dependent aperiodic reliance across EEG and ECG deep learning
• REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
• Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI
• Structure-preserving contrastive learning for spatial time series
• EEG-Bench: A Benchmark for EEG Foundation Models in Clinical Applications
• Aperiodic and Low-Frequency Spectral Bias in Reconstruction based EEG Foundation Models
• Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
• The Identity Trap in EEG Foundation Models: A Diagnostic Audit
• Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models
• Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Models
• What Do EEG Foundation Models Capture from Human Brain Signals?
• Batch Effects In Brain Foundation Model Embeddings
• CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding
• What EEG Foundation Models Encode: Dataset Identity and a Negative-Control Suite for Clinical Benchmarks

Related papers

• BrainWave: A Brain Signal Foundation Model for Clinical Applications
• Toward Robust, Reproducible, and Widely Accessible Intracranial Speech Brain-Computer Interfaces: A Comprehensive Narrative Review of Neural Mechanisms, Hardware, Algorithms, Evaluation, Clinical Pathways and Future Directions
• CytoNet: A Foundation Model for the Human Cerebral Cortex at Cellular Resolution
• Emergence of psychopathological computations in large language models
• NeuroAI and Beyond: Bridging Between Advances in Neuroscience and Artificial Intelligence
• Attraction to hierarchical feature memory explains orientation bias