arXiv AI
Jul 29
Foundation Models for EEG Are Blind to Long-Range Temporal Correlations: A Spectral-Temporal Dissociation Behind Their Cross-Population Fragility
arXiv:2607. 24834v1 Announce Type: cross Abstract: Objective.
Cross-Cohort Spectral-Temporal Dissociation in Frozen EEG Foundation-Model Representations
arXiv:2607. 24834v2 Announce Type: replace-cross Abstract: Objective.
Related stories
arXiv Machine Learning
Aug 4
What EEG Foundation Models Encode: Dataset Identity and a Negative-Control Suite for Clinical Benchmarks
arXiv:2607. 24519v2 Announce Type: replace Abstract: Pretrained EEG foundation models are proposed for clinical decoding, but whether reported gains transfer across populations or survive negative controls is unclear.
arXiv AI
Aug 17
A Negative-Control Protocol for Clinical EEG Foundation-Model Benchmarks: Dataset Identity and External-Cohort Stress Testing
arXiv:2607. 24519v3 Announce Type: replace-cross Abstract: EEG foundation-model gains may depend on cohort, montage, or probe design.
Hugging Face Trending Papers
Jul 27
Stress-Testing EEG Foundation Models for Clinical Decoding: Dataset Identity and Targeted Negative Controls
Pretrained EEG foundation models are increasingly proposed for clinical decoding, but their transfer across populations and robustness to negative controls remain unclear. We benchmark six models (LaBraM, EEGMamba, CBraMod, REVE, BENDR, and BIOT) on five clinical tasks across four datasets using frozen linear probes with leave-one-subject-out, subject-grouped, or explicitly identified recording-level splits.
arXiv AI
Jul 28
Stress-Testing EEG Foundation Models for Clinical Decoding: Dataset Identity and Targeted Negative Controls
arXiv:2607. 24519v1 Announce Type: cross Abstract: Pretrained EEG foundation models are increasingly proposed for clinical decoding, but their transfer across populations and robustness to negative controls remain unclear.
arXiv Machine Learning
Jun 8
The Identity Trap in EEG Foundation Models: A Diagnostic Audit
arXiv:2606. 06647v1 Announce Type: new Abstract: Objective.
arXiv Machine Learning
Sep 2
Lightweight Adaptation of EEG Foundation Models for Stroke Motor Imagery Decoding: Domain Shift and Subject-Level Robustness
The study investigates whether Low‑Rank Adaptation (LoRA) can adapt three pretrained EEG foundation models—LaBraM‑base, REVE‑base, and REVE‑large—for binary left‑ vs. right‑hand motor imagery decoding in stroke patients. Using subject‑wise five‑fold cross‑validation on the PhysioNet EEG Motor Movement/Imagery Dataset and a binary subset of the UET175 stroke dataset, LoRA significantly improved accuracy for LaBraM‑base (0.822) and REVE‑base (0.957) on the healthy cohort, but only REVE‑base LoRA achieved high performance (0.847±0.194) on stroke data, with a best mean accuracy of 0.952 in leave‑one‑subject‑out evaluation. The results demonstrate that healthy‑benchmark performance does not guarantee transfer to stroke EEG, highlighting the need for target‑domain adaptation and subject‑level assessment in rehabilitation BCIs.
arXiv Machine Learning
Aug 17
EEG-PRISM: Physiologically-Grounded Interpretability of Predictions by EEG Foundation Models
arXiv:2608. 13676v1 Announce Type: new Abstract: Objective: Foundation models represent the next advancement in AI for EEG analysis; however current explainable AI techniques provide attribution scores in the time-channel input space, which is mismatched to clinical intuition about EEG.
arXiv AI
Sep 7
BioSync: Transformer-Based Cross-Modal Fusion for a Multimodal Physiological Digital Biomarker
BioSync is a transformer-based model that fuses cardiac, neural, behavioral, and speech data from wearables and mobile devices into a continuous composite digital biomarker called the BioSync Index (BSI). The architecture uses multi-head self-attention on modality tokens and a linear branch for feature concatenation, inspired by latent-variable measurement theory. Evaluations on synthetic cohorts for cognitive decline and metabolic-autonomic conditions show BioSync achieving AUCs of 0.928 and 0.764 accuracy/F1 of 0.766, outperforming simple concatenation and other fusion strategies in most corruption scenarios.
arXiv AI
Sep 15
MANAS-2: Constrained Reconstruction for EEG Foundation Models
MANAS-2 is a new EEG foundation model that integrates a Raw‑Band Hybrid masked autoencoder with a physics‑motivated Constrained Reconstruction (ConRec) regularizer. ConRec penalizes RMS energy differences in short temporal windows, guiding the encoder toward oscillatory‑envelope organization. Across seven held‑out EEG datasets, adding ConRec improves spectral‑power recovery (R² from 0.860 to 0.906) and band‑energy dynamics (R² from 0.283 to 0.354), while maintaining strong temporal waveform recoverability and outperforming leading EEG models on downstream tasks.
arXiv Statistics ML
Sep 22
Subspace Learning with Interval-Censored Likelihoods for Dequantizing Percept PC LFP Snapshots
The paper addresses the problem of quantization artifacts in spectral data from the Medtronic Percept PC deep brain stimulation device, which stores local field potential amplitudes as 16‑bit integers. By treating dequantization as an interval‑censored subspace estimation problem, the authors evaluate five correction methods and find that quantized probabilistic PCA most effectively reduces spurious spectral peaks while preserving true peaks and maintaining a low noise floor. The study demonstrates that over 20% of detected peaks in clinical spectra are artifacts, highlighting the need for accurate dequantization in biomarker pipelines.
arXiv AI
Aug 5
Cross-Anesthetic ECoG State Decoding Fails at the Decision Threshold, Not the Representation
arXiv:2608. 02646v1 Announce Type: cross Abstract: Decoders of anesthetic state from cortical activity fail across drug classes, most notoriously ketamine, but reported accuracy cannot say whether the neural representation or only the decision threshold has failed; we separate the two in a controlled preparation with ground-truth labels.