Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.
Code and weights are not public, and there's no licence. Watch for a code release.
- Signals
- ECG, EEG, EMG, EOG
- Form factor
- clinical_PSG
- Architecture
EXG encoder aligned to the Brant-2 EEG foundation model (patch- and sequence-level InfoNCE)
- Type
- Foundation model
- Form factor
- Clinical PSG
- Parameters
- Not reported
- Architecture
- EXG encoder aligned to the Brant-2 EEG foundation model (patch- and sequence-level InfoNCE)
- Venue
- Not reported
- Year
- Not reported
- arXiv
- Not reported
- DOI
- Not reported
- Code
- Not released
- Weights
- Not released
- Licence
- Not reported
- Caveats
- Not reported
- Datasets
- Not reported
- Added
- Oct 19, 2026
- Updated
- Oct 19, 2026
Original description
Firstly, based on the EEG foundation model, the EXG encoder is trained by the alignment between synchronously collected EEG and EXG data. Then, the EEG and EXG encoders, capable of learning strong representations from EEG and EXG signals, are applied to various downstream tasks in diverse scenarios.
Brant-X employs the EEG foundation model Brant-2 as its EEG encoder to transfer the rich knowledge from the EEG foundation model to other physiological signals.
To serve as a research resource for multi-type signal modeling, we summarize those public datasets that contain two or more types of signals among EEG, EOG, ECG, and EMG, as presented here.
Verbatim fromGitHub· Description from the repository README
How it works
- Architecture
- EXG encoder aligned to the Brant-2 EEG foundation model (patch- and sequence-level InfoNCE)
- Inputs
- ECG, EEG, EMG, EOG
- Approach
- eeg fm · alignment · brant 2
Datasets
Papers· 1
Cite
APA
Brant-X. (n.d.).
BibTeX
@misc{brantxbrantx,
title = {{Brant-X}}
}Built from the hub record. Check it against the publisher before submitting.
History
Added to the ChatPPG research hub