Brain4FMs: A Benchmark of Foundation Models for Electrical Brain Signal
Authors:
- Fanqi ShenFSFanqi Shen
- Enhong YangEYEnhong Yang
- Jiahe LiJLJiahe Li
- Junru HongJHJunru Hong
- Xiaoran PanXPXiaoran Pan
- Zhizhang YuanZYZhizhang Yuan
- Meng LiMeng Li
- Yang YangYYYang Yang
Preprint
Abstract
Brain Foundation Models (BFMs) are transforming neuroscience by enabling scalable and transferable learning from neural signals, advancing both clinical diagnostics and cutting-edge neuroscience exploration. Their emergence is powered by large-scale clinical recordings, particularly electroencephalography (EEG) and intracranial EEG, which provide rich temporal and spatial representations of brain dynamics. However, despite their rapid proliferation, the field lacks a unified understanding of existing methodologies and a standardized evaluation framework. To fill this gap, we map the benchmark design space along two axes: (i) from the model perspective, we organize BFMs under a self-supervised learning (SSL) taxonomy; and (ii) from the dataset perspective, we summarize common downstream tasks and curate representative public datasets across clinical and human-centric neurotechnology applications. Building on this consolidation, we introduce Brain4FMs, an open evaluation platform with plug-and-play interfaces that integrates 15 representative BFMs and 18 public datasets. It enables standardized comparisons and analysis of how pretraining data, SSL strategies, and architectures affect generalization and downstream performance, guiding more accurate and transferable BFMs. The code is available at https://anonymous.4open.science/r/Brain4FMs-85B8.Keywords
All Related Versions
This publication has 40 references indexed in Scilit:
- Towards neural foundation models for vision: Aligning EEG, MEG, and fMRI representations for decoding, encoding, and modality conversionInformation Fusion, 2025
- Multi-modal cross-domain self-supervised pre-training for fMRI and EEG fusionNeural Networks, 2024
- Chisco: An EEG-based BCI dataset for decoding of imagined speechScientific Data, 2024
- A resting-state EEG dataset for sleep deprivationScientific Data, 2024
- Autoregressive models in environmental forecasting time series: a theoretical and application reviewEnvironmental Science and Pollution Research, 2023
- A survey on deep learning-based non-invasive brain signals: recent advances and new frontiersJournal of Neural Engineering, 2021
- End-to-end sleep staging using convolutional neural network in raw single-channel EEGBiomedical Signal Processing and Control, 2021
- Multicenter intracranial EEG dataset for classification of graphoelements and artifactual signalsScientific Data, 2020
- A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year updateJournal of Neural Engineering, 2018
- ISRUC-Sleep: A comprehensive public dataset for sleep researchersComputer Methods and Programs in Biomedicine, 2016