The paper evaluates five publicly released EEG foundation models and an in‑house JEPA‑style model using a protocol that includes three key controls: an untrained encoder, spectral band‑power features, and a probe layer selected without test‑set look‑ahead. The study finds that selecting the probe layer by test score can modestly improve peak performance and alter the peak‑versus‑output relationship, that random initialization can match or surpass pretraining on certain tasks, and that full fine‑tuning rarely yields gains beyond seed variability. These findings lead the authors to propose four new reporting practices and to release all experimental results for re‑analysis.
arXiv:2606. 00815v1 Announce Type: new Abstract: Electroencephalography (EEG) supports a variety of brain-computer interface (BCI) tasks ranging from brain-state monitoring to human-LLM interactions.
arXiv:2610.07484v1 Announce Type: new Abstract: Self-supervised EEG models often reconstruct masked waveforms or predict discrete codes. We study a task-aligned alternative: masked band-power predict...
arXiv:2508. 17742v3 Announce Type: replace-cross Abstract: Electroencephalography foundation models (EEG-FMs) have advanced brain signal analysis, but the lack of standardized evaluation benchmarks impedes model comparison and scientific progress.
arXiv:2609.36609v1 Announce Type: cross Abstract: Electroencephalography (EEG) analysis requires careful choices in preprocessing, statistical modeling, and machine learning because EEG signals are h...
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.
The study investigates whether adding specialized modules—cross‑depth Attention Residuals (AttnRes) and soft‑routed expert banks—to a fully fine‑tuned EEG foundation model improves performance on various EEG decoding tasks. Across four datasets (FACED, ISRUC, SEED‑V, PhysioNet‑MI), AttnRes alone boosts mean balanced accuracy on three datasets, while the full model with experts only benefits two. However, these gains come with significant computational overhead, and the effects are dataset‑dependent rather than consistently positive.
The study compares six state‑of‑the‑art sleep‑staging foundation models on the MESA polysomnography dataset under three signal conditions: EEG only, ECG only, and EEG+ECG. Results show that EEG alone yields the highest accuracy (BIOT macro‑F1 = 0.7237), while switching to ECG alone incurs a consistent accuracy loss of about 0.35 macro‑F1 and reduces data rate to one‑third. Adding ECG to EEG offers little benefit for most models, indicating that EEG carries most of the sleep‑staging signal and that wearable‑compatible ECG alone is a viable but less accurate alternative.
NeuroAtlas is the largest EEG benchmark to date, comprising 42 datasets and 260,000 hours of clinical EEG data across epilepsy, sleep medicine, brain age estimation, and brain‑computer interfaces. The study evaluates foundation models (FMs) for EEG against supervised baselines and generic time‑series FMs, finding that EEG‑specific FMs do not consistently outperform generic ones. It also demonstrates that standard machine‑learning metrics are inadequate for clinical relevance, advocating for task‑specific measures such as event‑level decision quality, hypnogram features, and brain‑age gap.
Brain4FMs is a unified benchmark for evaluating brain foundation models (BFMs) on both scalp EEG and intracranial EEG (iEEG). It incorporates 17 representative models and 21 public datasets spanning clinical diagnosis, sleep staging, communication, and affective computing, and offers dataset-aware preprocessing, cross‑subject evaluation, and standardized downstream workflows. The benchmark highlights that no single BFM consistently outperforms others across all tasks, modalities, and adaptation protocols, prompting further exploratory analyses of model‑specific spatial, spectral, and discrete representations.
EEG-AS is an instance-level algorithm selection framework designed for EEG foundation models. It characterizes each EEG instance using latent embeddings, handcrafted neurophysiological features, and an anchor foundation model, then learns to reconstruct the behaviors of other foundation models from privileged prediction tokens. During inference, EEG-AS estimates these behaviors without running the full model portfolio, enabling efficient selection among seven EEG foundation models and significantly reducing the performance gap between the single best solver and the oracle upper bound across seven public EEG benchmarks.
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:2601. 17883v3 Announce Type: replace Abstract: Electroencephalography (EEG) foundation models (FMs) have recently emerged as a promising paradigm for brain-computer interfaces, aiming to learn transferable neural representations from large-scale heterogeneous recordings.