AAAI 2026technical0 citations

BraSTORM: A Dual-Branch Self-Supervised Framework for EEG Representation Learning via Input-Level Spatio-Temporal Decomposition

Yifan Wang, Der-Horng Lee, Bruce X.B. Yu

Abstract

Prevalent pre-training strategies for Brain-Computer Interfaces (BCIs) are often constrained by spatio-temporal entanglement. This critical issue arises from processing multi-channel Electroencephalography (EEG) signals as monolithic sequences, which intertwines the signal

BibTeX
@inproceedings{aaai2026_brastormadualbra,
  title = {BraSTORM: A Dual-Branch Self-Supervised Framework for EEG Representation Learning via Input-Level Spatio-Temporal Decomposition},
  author = {Yifan Wang and Der-Horng Lee and Bruce X.B. Yu},
  booktitle = {AAAI 2026},
  year = {2026}
}
BraSTORM: A Dual-Branch Self-Supervised Framework for EEG Representation Learning via Input-Level Spatio-Temporal Decomposition · AAAI 2026