arXiv Machine Learning

SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction

SPERA is a new EEG foundation model that predicts in latent space using a joint-embedding predictive architecture. It incorporates a Legendre-polynomial spatial prior into attention to handle varying scalp electrode geometries, and adds factorized temporal and spatial attention with periodic full-attention blocks, plus a relational spectral regularizer to align latent similarity with spectral views. Trained on about 80,000 hours of EEG from 29,048 subjects across 106 datasets, SPERA achieves the highest average balanced accuracy on nine downstream tasks in clinical, cognitive, and BCI domains, while demonstrating strong parameter efficiency and robustness to different recording conditions.

arXiv AI

Sep 28

Neural State Prediction: Obstructing Shortcut Learning in EEG Foundation Models

Neural State Prediction (NSP) is a latent‑predictive framework designed to curb shortcut learning in EEG foundation models. By using a target encoder updated with an exponential moving average, identity residualization, and topology‑separated context, NSP constrains both the prediction target and the available context. Trained on 2.2 million EEG segments, NSP outperforms baselines on 14 datasets in the EEG‑FM‑Bench, achieving 63.94 % macro balanced accuracy.

By Kieren Yu, Ziyang Liu, Chang Huang, Jintai Chen, Kaishun Wu

fine-tuning

arXiv AI

Sep 2

EEG-AS: Instance-Level Foundation Model Selection for EEG Foundation Models via Behavior Reconstruction

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.

By Yunzhen Zhang, Ruoxi Piao, Hasan Onur Keles, Mustafa Misir

rag benchmarks

arXiv AI

Aug 26

Taming foundation model with invariance-oriented pre-training for broad-spectrum EEG analysis across signal-level, brain-state, and brain-health tasks

arXiv:2608.24597v1 Announce Type: cross Abstract: Electroencephalography (EEG) is a widely used window into human brain function, but most EEG models remain tied to a one-dataset-one-model supervised...

By Yulong Dou, Han Wu, Guo Chen, Fangmao Ju, Zhiming Cui, Dinggang Shen

fine-tuning benchmarks

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.

By Deeksha M Shama, Punnisa Amornsirikul, Archana Venkataraman

safety

arXiv Machine Learning

4d ago

BrainPro: Process-conditioned Pretraining with Topographic Retrieval for Large EEG Models

BrainPro is a process‑conditioned self‑supervised pretraining framework for large EEG models that addresses two underexplored challenges: the underuse of mental‑process cues in masked pretraining and the variability of electrode montages across datasets. It maps dataset‑specific montages to a universal channel‑region template, retrieves spatial filters to create a topographically aligned basis, and learns a shared encoder along with process‑specific branches conditioned on protocol cues. Experiments on nine public BCI benchmarks show that BrainPro outperforms baselines, with ablations indicating that topographic retrieval and process‑conditioned representation learning jointly enhance EEG decoding.

By Yi Ding, Muyun Jiang, Weibang Jiang, Shuailei Zhang, Xinliang Zhou, Chenyu Liu, Shanglin Li, Yong Li, Cuntai Guan

benchmarks

arXiv AI

Aug 14

EEG-PRIME: Prototype-Aligned Representation Learning with Multi-Level Conditioning for EEG Decoding

arXiv:2608. 13072v1 Announce Type: new Abstract: Electroencephalography (EEG) decoding models often generalize poorly across datasets and subjects due to domain shifts in acquisition protocols and individual neurophysiology.

By Shuailei Zhang, Muyun Jiang, Wei Zhang, Jinbo Chen, Zhiwei Guo, Yong Li, Yi Ding, Cuntai Guan

rag fine-tuning benchmarks

arXiv Machine Learning

Sep 30

Best Practices in EEG Analysis: Preprocessing, Modeling, and Machine Learning

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...

By Parsa Razmara, Woojae Jeong, Aditya Kommineni, Raymundo Cassani, Richard Leahy, Takfarinas Medani

benchmarks

arXiv Machine Learning

Sep 1

MEL: Coordinate-Preserving EEG Tokenization for fMRI Translation

arXiv:2608.29304v1 Announce Type: new Abstract: Translating electroencephalography (EEG) into functional magnetic resonance imaging (fMRI) is important for medical neuroimaging, clinical brain-state...

By Xiangyu Liu, Zeting Yan, Zhitong Yin, Boyang Li, Xi Zhang

nlp multimodal benchmarks

arXiv Machine Learning

Aug 6

STEAM: A Spatio-TEmporal Alignment Mixture-of-Experts Model with Hierarchical Pre-training for EEG Decoding

arXiv:2608. 02070v2 Announce Type: replace-cross Abstract: Brain-computer interfaces (BCIs) have been widely used in motor rehabilitation, disease diagnosis, and other neural engineering scenarios.

By Zhu Chen, Dingkun Liu, Yuheng Chen, Dongrui Wu

safety

arXiv Machine Learning

Aug 4

STEAM:ASpatio-TEmporal Alignment Mixture-of-Experts Model with Hierarchical Pre-training for EEG Decoding

arXiv:2608. 02070v1 Announce Type: cross Abstract: Brain-computer interfaces (BCIs) have been widely used in motor rehabilitation, disease diagnosis, and other neural engineering scenarios.

By Zhu Chen, Dingkun Liu, Yuheng Chen, Dongrui Wu

safety

arXiv Machine Learning

Aug 13

Continuous-Latent Predictive Modeling with Semantic Alignment for EEG-Language Foundation Models

arXiv:2608. 11656v1 Announce Type: new Abstract: Recent advances in EEG foundation models have demonstrated the potential of large-scale pretraining to enable generalizable neural decoding across subjects, recording environments, and datasets.

By Myeong-Ju Cho, Hye-Bin Shin, Seo-Hyun Lee, Seong-Whan Lee

llms rag diffusion benchmarks safety

arXiv Machine Learning

Sep 7

Brain4FMs: A Benchmark of Foundation Models for Electrical Brain Signal

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.

By Fanqi Shen, Enhong Yang, Jiahe Li, Junru Hong, Xiaoran Pan, Zhizhang Yuan, Meng Li, Yang Yang

benchmarks

Related stories