B[FM]^2 pretrains an EEG foundation model on raw signals with flow matching and SplitUNet, reaching SOTA on 7 of 9 tasks using ~30x less data and generating neurologist-indistinguishable synthetic EEG.
hub
arXiv preprint arXiv:2106.11170 (2021)
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
verdicts
UNVERDICTED 16representative citing papers
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 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.
DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
Generative Visual Grounding creates instance-specific visual proxy images from EEG signals to enhance MLLM understanding of brain activity beyond text-only alignment.
PRiSE-EEG is a prior-guided EEG foundation model that allocates shared and specialized experts across depth using CKA-derived sigmoid mappings and reports strong cross-paradigm results on 12 benchmarks.
Brain-OF is a multimodal foundation model for fMRI, EEG and MEG using any-resolution sampling, DINT attention with sparse MoE, and masked temporal-frequency pretraining on ~40 datasets to achieve superior downstream performance.
UniMind unifies multi-task brain decoding from EEG by bridging signals to LLMs via a Neuro-Language Connector and dynamic task queries, outperforming prior models by 12% on average across ten datasets.
CodeBrain introduces a decoupled TFDual-Tokenizer and multi-scale EEGSSM architecture for an EEG foundation model pretrained on a large corpus, claiming strong generalization across eight downstream tasks and ten datasets.
TFM-Tokenizer learns a vocabulary of time-frequency motifs from single-channel EEG via a dual-path masked architecture and encodes signals into discrete tokens, reporting up to 11% Cohen's Kappa gains on benchmarks and 14% on ear-EEG sleep staging.
A signal foundation model trained on over 100,000 minutes of sEEG plus a language model achieves 0.978 contact-level PPV for epileptogenic zone identification under leave-one-patient-out evaluation.
MSCGC-KAN adds multi-scale causal graph convolution and Kolmogorov-Arnold feature mapping as a structured task head on a pre-trained CBraMod backbone, reporting balanced accuracy gains of 5.91 and 2.03 points on FACED and SEED-VII datasets over a linear baseline.
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.
TGSN reports 97.78% accuracy on AD/FTD classification and RMSE of 1.93 for MMSE prediction on the XY02 EEG dataset, outperforming baselines by large margins.
NeuroWeaver reformulates EEG pipeline design as constrained evolutionary optimization with domain-informed initialization, yielding lightweight pipelines that outperform task-specific methods and match foundation models on five benchmarks.
EEG-TransNet combines wavelet denoising, ResNet feature extraction, local self-attention, and a fuzzy-attention synchronous transformer to outperform prior methods on BETA, SEED, and DepEEG datasets for EEG emotion recognition.
citing papers explorer
-
B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet
B[FM]^2 pretrains an EEG foundation model on raw signals with flow matching and SplitUNet, reaching SOTA on 7 of 9 tasks using ~30x less data and generating neurologist-indistinguishable synthetic EEG.
-
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.
-
DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG
DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
-
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.
-
PRiSE-EEG: A Prior-Guided Foundation Model with Depth-Stratified Experts for Cross-Paradigm EEG Representation Learning
PRiSE-EEG is a prior-guided EEG foundation model that allocates shared and specialized experts across depth using CKA-derived sigmoid mappings and reports strong cross-paradigm results on 12 benchmarks.
-
Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG
Brain-OF is a multimodal foundation model for fMRI, EEG and MEG using any-resolution sampling, DINT attention with sparse MoE, and masked temporal-frequency pretraining on ~40 datasets to achieve superior downstream performance.
-
UniMind: Unleashing the Power of LLMs for Unified Multi-Task Brain Decoding
UniMind unifies multi-task brain decoding from EEG by bridging signals to LLMs via a Neuro-Language Connector and dynamic task queries, outperforming prior models by 12% on average across ten datasets.
-
CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model
CodeBrain introduces a decoupled TFDual-Tokenizer and multi-scale EEGSSM architecture for an EEG foundation model pretrained on a large corpus, claiming strong generalization across eight downstream tasks and ten datasets.
-
Tokenizing Single-Channel EEG with Time-Frequency Motif Learning
TFM-Tokenizer learns a vocabulary of time-frequency motifs from single-channel EEG via a dual-path masked architecture and encodes signals into discrete tokens, reporting up to 11% Cohen's Kappa gains on benchmarks and 14% on ear-EEG sleep staging.
-
Foundation Models for Epileptogenic Zone Identification in Drug-Resistant Epilepsy
A signal foundation model trained on over 100,000 minutes of sEEG plus a language model achieves 0.978 contact-level PPV for epileptogenic zone identification under leave-one-patient-out evaluation.
-
MSCGC-KAN: Multi-scale Causal Graph Convolution and Kolmogorov-Arnold Feature Mapping for EEG Emotion Recognition
MSCGC-KAN adds multi-scale causal graph convolution and Kolmogorov-Arnold feature mapping as a structured task head on a pre-trained CBraMod backbone, reporting balanced accuracy gains of 5.91 and 2.03 points on FACED and SEED-VII datasets over a linear baseline.
-
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.
-
Task-guided Spatiotemporal Network with Diffusion Augmentation for EEG-based Dementia Diagnosis and MMSE Prediction
TGSN reports 97.78% accuracy on AD/FTD classification and RMSE of 1.93 for MMSE prediction on the XY02 EEG dataset, outperforming baselines by large margins.
-
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 models on five benchmarks.
-
Transformer Based Model for Spatiotemporal Feature Learning in EEG Emotion Recognition
EEG-TransNet combines wavelet denoising, ResNet feature extraction, local self-attention, and a fuzzy-attention synchronous transformer to outperform prior methods on BETA, SEED, and DepEEG datasets for EEG emotion recognition.