cs.LGSep 29, 2025

LEAF: Language-EEG Aligned Foundation Model for Brain-computer interfaces

Authors: Muyun Jiang, Shuailei Zhang, Zhenjie Yang, Mengjun Wu, Wei Zhang, Weibang Jiang, Chenyu Liu, Zhiwei Guo, 

Organizations: Nanyang Technological University, Singapore. · Shanghai Jiao Tong University, China. · University of Science and Technology Beijing, China. · Southeast University, China.

Abstract

Electroencephalography (EEG) foundation models learn transferable representations for brain-computer interfaces, but existing approaches treat tasks and labels as discrete targets and fail to use the semantic structure of natural-language task instructions to guide representation learning. We present LEAF, a foundation model for EEG-Language Alignment with Semantic Task Instruction and Querying. LEAF integrates task-aware semantic guidance to produce structured and linguistically aligned EEG embeddings, thereby enhancing decoding robustness and transferability. In the EEG pretraining stage, we introduce a joint Spectral-Temporal Reconstruction (STR) framework that captures the coupled spectral rhythms and temporal dynamics of EEG signals. STR applies randomized spectral perturbation to enhance frequency robustness and uses two complementary temporal objectives to learn both contextual and sequential structure. In the EEG-Language alignment stage, we propose the Instruction-conditioned Q-Former (IQF). This query-based cross-attention transformer injects instruction embeddings into EEG tokens and achieves semantic alignment with textual label embeddings through learnable queries. We evaluate LEAF on 16 downstream datasets spanning motor imagery, emotion recognition, steady-state visual evoked potentials, covert speech, and mental-workload decoding. Under supervised finetuning, LEAF achieves the best balanced accuracy on 12 of the 16 datasets and the strongest average performance across the evaluated paradigms. Further analyses show that instruction conditioning reduces intra-class variation, increases inter-class separation, and aligns EEG representations more closely with textual class prototypes. These findings support the use of task instructions as semantic priors for transferable EEG decoding. Code is available at https://github.com/Jiang-Muyun/LEAF.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Continuous-Latent Predictive Modeling with Semantic Alignment for EEG-Language Foundation Models

    Aug 12, 2026Myeong-Ju Cho, Hye-Bin Shin, Seo-Hyun Lee +1EEG DecodingPredictive Representation Learning

  2. EEG-PRIME: Prototype-Aligned Representation Learning with Multi-Level Conditioning for EEG Decoding

    Aug 13, 2026Shuailei Zhang, Muyun Jiang, Wei Zhang +5Cross-Subject EEG DecodingZero-Shot Learning

  3. Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction

    Mar 17, 2026Saarang Panchavati, Uddhav Panchavati, Hiroki Nariai +2EEG Foundation ModelsSelf-Supervised Time Series Representation Learning