LEAF: Language-EEG Aligned Foundation Model for Brain-computer interfaces
cs.LG
Submitted: 2025-09-29
Updated: 2026-10-31
License: http://creativecommons.org/licenses/by/4.0/
The gist: Electroencephalography (EEG) foundation models learn transferable representations for brain-computer interfaces…
Terminology
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.
Sources
- Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI
- CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding
- LLaMA: Open and Efficient Foundation Language Models
- NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals
- Towards Robust Multimodal Physiological Foundation Models: Handling Arbitrary Missing Modalities
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Learning Visual Reasoning Without Strong Priors
- Transformer-based Spatial-Temporal Feature Learning for EEG Decoding
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis