eeg

DCRA introduces a diffusion-conditioned representation alignment framework to enhance robustness in time-series learning, particularly for clinical signals like EEG and ECG, by aligning representations across noise levels.

This paper proposes RAMamba-Net, a reliability-aware multimodal fusion network using EEG and EOG signals for auditory attention detection, which enhances accuracy and robustness over unimodal methods.

This paper challenges the assumption that more components improve performance in P300 brain-computer interface spellers, revealing that components can exhibit anti-synergy and their effectiveness depends on the quality of the underlying EEG pipeline.

The paper proposes EEG-AS, an algorithm selection framework that enables instance-level selection among multiple EEG foundation models by reconstructing their behaviors, thereby improving neural decoding performance.

EEG-VID introduces task-guided latent predictive pretraining to improve EEG decoding under session and subject shifts, achieving above-chance target selection in assistive robotics scenarios.

This paper reformulates EEG-based reaction-time decoding as event-time posterior modeling, using behavioral latency as weak supervision to improve prediction accuracy.

This research uses non-invasive EEG and contrastive learning to decode words during silent reading, showing scalable lexical information recovery that scales with data volume.

The paper presents NanoSleep, a parameter-efficient hybrid temporal convolutional network for automatic sleep stage classification using single-channel EEG, designed for wearable and home-based monitoring on resource-constrained devices.

Delta2Gamma is a self-supervised learning framework that decomposes EEG signals into frequency bands and uses adaptive contrastive learning for Alzheimer's disease detection, achieving 92.4% accuracy.

This paper proposes SW-ProxyCE, a zero-query adversarial attack framework that transfers from public EEG encoders to private downstream models, demonstrating security risks in EEG foundation models.

EEG-PRISM is a post-hoc attribution method that maps EEG foundation model predictions to physiologically relevant domains like frequency and source, enhancing interpretability for clinical applications such as epilepsy and autism.

Research indicates that during REM sleep, the brain shifts its attention inward, as observed through EEG recordings.

An experimental BCI system for TouchDesigner that reads live EEG signals, classifies mental state, and autonomously generates responsive AI video for meditation, designed to work with OpenBCI, Muse, Neurosity, and other headsets.

This paper presents a learning-based framework that models individual scorer behavior via confusion matrices to derive more robust sleep stage labels from multiple experts, improving accuracy on DOD-H and DOD-O datasets.

The paper proposes BLPM, an EEG-language foundation model that uses continuous latent predictive modeling and semantic alignment to map EEG signals to text embeddings, achieving generalizable neural decoding across diverse tasks and datasets.

This paper proposes OSPDIM, a source-free online unsupervised domain adaptation framework for EEG-based BCIs that corrects geometric misalignment caused by class-imbalanced label shifts on the Riemannian manifold, outperforming standard alignment methods in online scenarios.

BrainBench is a new unified benchmark for evaluating large language models on comprehensive, instruction-conditioned EEG understanding, covering 17 datasets, 172 tasks, and over 4K real-data instances. The paper evaluates 13 LLMs across two execution paradigms, showing that EEG competence varies by model and operationalization.

This paper proposes a multi-representation deep learning framework combining CNNs, LSTMs, and recurrence plot analysis to characterize alpha and gamma EEG biomarkers in Fragile X Syndrome, showing improved classification over single-modality baselines.

A comprehensive review of technological advances in detecting and managing cognitive impairment in older adults, covering EEG, neuroimaging, blood-based biomarkers, digital tools, and AI/ML integration, with a focus on challenges like external validation and equitable deployment.

This paper examines how evaluation protocols affect reported accuracy in EEG emotion recognition, using a DGCNN on SEED and SEED-IV datasets. It demonstrates that subject-dependent, subject-disjoint, and cross-session evaluations answer different questions, and that checkpoint selection and test-set reuse can inflate accuracy.