REVIEW 27 cited by
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI
read the original abstract
The current electroencephalogram (EEG) based deep learning models are typically designed for specific datasets and applications in brain-computer interaction (BCI), limiting the scale of the models and thus diminishing their perceptual capabilities and generalizability. Recently, Large Language Models (LLMs) have achieved unprecedented success in text processing, prompting us to explore the capabilities of Large EEG Models (LEMs). We hope that LEMs can break through the limitations of different task types of EEG datasets, and obtain universal perceptual capabilities of EEG signals through unsupervised pre-training. Then the models can be fine-tuned for different downstream tasks. However, compared to text data, the volume of EEG datasets is generally small and the format varies widely. For example, there can be mismatched numbers of electrodes, unequal length data samples, varied task designs, and low signal-to-noise ratio. To overcome these challenges, we propose a unified foundation model for EEG called Large Brain Model (LaBraM). LaBraM enables cross-dataset learning by segmenting the EEG signals into EEG channel patches. Vector-quantized neural spectrum prediction is used to train a semantically rich neural tokenizer that encodes continuous raw EEG channel patches into compact neural codes. We then pre-train neural Transformers by predicting the original neural codes for the masked EEG channel patches. The LaBraMs were pre-trained on about 2,500 hours of various types of EEG signals from around 20 datasets and validated on multiple different types of downstream tasks. Experiments on abnormal detection, event type classification, emotion recognition, and gait prediction show that our LaBraM outperforms all compared SOTA methods in their respective fields. Our code is available at https://github.com/935963004/LaBraM.
Forward citations
Cited by 27 Pith papers
-
EvoBrain: Continual Learning of EEG Foundation Models Across Heterogeneous BCI Tasks
EvoBrain introduces a continual learning method with Neuro-Spectral Task Normalization and Response-Affinity Distillation to enable unified EEG decoding across heterogeneous BCI tasks.
-
CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models
CaMBRAIN introduces a causal Mamba-based SSM with a multi-stage self-supervised training pipeline that achieves SOTA results on three EEG datasets while enabling linear-time long-range inference.
-
Let EEG Models Learn EEG
JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising me...
-
NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
NeuroAtlas benchmarks foundation models on 42 EEG datasets and reports that EEG-specific models do not consistently outperform generic time-series models, standard metrics miss clinical utility, and rankings vary by domain.
-
Neuroprobe: Evaluating Intracranial Brain Responses to Naturalistic Stimuli
Neuroprobe is a new suite of decoding tasks on the BrainTreebank iEEG dataset for evaluating multi-modal language processing in the brain during naturalistic movie viewing.
-
Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech
PNA decomposes MEG recordings via ICA, isolates artifact components using EOG/ECG references, and re-injects scaled artifacts into clean data to train decoders that are invariant to physiological noise, improving imag...
-
I\textsuperscript{2}RiMA: Spectral Riemannian Representation with Temporal Attention for Mental Stress Detection based on EEG Signals
I²RiMA achieves up to 82.78% balanced accuracy in cross-subject EEG stress detection by mapping frequency-specific covariances to the SPD tangent space, aggregating spectral clusters, and applying intra-inter temporal...
-
Device Passport: Enabling Spatio-Temporal Pretrained Models to Generalize Across Input Layouts
Device Passport improves cross-layout transfer for biosignal models by learning expert mixture models from each channel's functional activity and metadata, outperforming baselines in transfer regimes.
-
Next-Token Prediction Learns Generalisable Representations of Sleep Physiology
Next-token prediction on multi-modal tokenized sleep signals yields embeddings that match supervised performance with far less labels and generalize to daytime heart data.
-
Channel-Oriented Design for EEG-to-Music Reconstruction
Introduces a channel-oriented design using per-electrode tokenization, multi-view self-distillation, and structured channel dropout within an encoding-alignment-decoding pipeline to improve EEG-to-music reconstruction...
-
MyoSem: Aligning Electromyography to Natural-Language Action Semantics for Hand Action Understanding
MyoSem is a multimodal alignment framework that maps EMG signals to text-based action semantics for bidirectional retrieval and improved generalization in hand action understanding.
-
Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs
Generative Visual Grounding creates visual proxy images from EEG to enhance MLLM understanding of brain signals beyond text-only alignment.
-
Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs
Generative Visual Grounding creates instance-specific visual proxy images from EEG signals to enhance MLLM understanding of brain activity beyond text-only alignment.
-
Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.
-
LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis
LLM-based refinement of edges in transformer-constructed EEG graphs improves seizure detection accuracy and produces cleaner, more interpretable structures on the TUSZ dataset.
-
OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural Tokens
OmniMouse demonstrates data-driven scaling in multi-task brain models on a 150B-token neural dataset, achieving SOTA across prediction, decoding, and forecasting while model size gains saturate.
-
PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL
PRISM-CTG is the first large-scale foundation model for cardiotocography that uses multi-view self-supervised learning on unlabeled data to learn transferable representations, outperforming baselines on seven downstre...
-
Bridging scalp and intracranial EEG in BCI via pretrained neural representations and geometric constraint embedding
A framework combining pretrained neural representations, geometric constraint embedding, and multidimensional diffusion synthesizes enhanced EEG signals that recover neural activity patterns lost in scalp-to-intracran...
-
fMRI-LM: Towards a Universal Foundation Model for Language-Aligned fMRI Understanding
fMRI-LM builds a foundation model that aligns fMRI signals with language through tokenization, LLM adaptation, and instruction tuning to enable semantic understanding of brain activity.
-
MindAU: EEG-Conditioned Facial Action Unit Editing via Dual-Stream Manifold Alignment
MindAU is a dual-stream manifold alignment system that conditions a multimodal diffusion editor on EEG signals to perform fine-grained, identity-preserving facial action unit edits.
-
BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language
BrainJanus presents a unified autoregressive model with a brain tokenizer that maps between neural activity, vision, and language for encoding and decoding tasks.
-
CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings
Pretrained scalp-EEG foundation models can be transferred to ECoG via adapters and fine-tuning to match or exceed subject-specific baselines on regression tasks while requiring far less per-patient data.
-
Benchmarking ERP Analysis: Manual Features, Deep Learning, and Foundation Models
A unified benchmark across 12 ERP datasets finds that foundation models and deep learning generally outperform traditional manual features for stimulus classification and disease detection, with specific embedding str...
-
NAPS: Attention-Based Fusion of Heterogeneous Physiological Signals
NAPS fuses heterogeneous physiological signals via attention-based aggregation on frozen unimodal encoders to achieve state-of-the-art generalization in sleep staging across datasets.
-
An Efficient Self-Supervised Framework for Long-Sequence EEG Modeling
EEGM2 is a Mamba-2 integrated self-supervised model for EEG that claims linear complexity and state-of-the-art performance on long-sequence modeling and classification tasks.
-
Towards Unified Multi-task EEG Analysis with Low-Rank Adaptation
MTEEG uses task-specific LoRA modules to jointly adapt a pre-trained EEG model across multiple tasks, outperforming single-task baselines on most metrics in evaluations on six downstream tasks.
-
NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines
NeuroWeaver reformulates EEG pipeline design as constrained evolutionary optimization with domain-informed initialization, yielding lightweight pipelines that outperform task-specific methods and match foundation mode...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.