ELASTIQ: EEG-Language Alignment with Semantic Task Instruction and Querying

2025-09-29

AI Summary

Current EEG foundation models struggle to effectively integrate natural language instructions as semantic priors, limiting interpretability and cross-task generalization of learned representations. To address this, we propose the first instruction-conditioned EEG representation learning framework, explicitly modeling natural language task instructions as semantic guidance priors. Our approach introduces a spectro-temporal reconstruction module and an instruction-conditioned Q-Former, jointly leveraging frequency/time-domain masking and cross-modal attention to achieve multimodal semantic alignment. We comprehensively evaluate on 20 EEG datasets spanning five task categories: our method achieves state-of-the-art performance on 14 datasets, with significant average gains, markedly improved decoding robustness, and superior cross-task transferability. The core contribution is the establishment of a unified EEG–language joint semantic space, enabling interpretable, instruction-driven brain–computer interfaces—a novel paradigm for controllable and explainable neural decoding.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Recent advances in electroencephalography (EEG) foundation models, which capture transferable EEG representations, have greatly accelerated the development of brain-computer interfaces (BCI). However, existing approaches still struggle to incorporate language instructions as prior constraints for EEG representation learning, limiting their ability to leverage the semantic knowledge inherent in language to unify different labels and tasks. To address this challenge, we present ELASTIQ, a foundation model for EEG-Language Alignment with Semantic Task Instruction and Querying. ELASTIQ integrates task-aware semantic guidance to produce structured and linguistically aligned EEG embeddings, thereby enhancing decoding robustness and transferability. In the pretraining stage, we introduce a joint Spectral-Temporal Reconstruction (STR) module, which combines frequency masking as a global spectral perturbation with two complementary temporal objectives: random masking to capture contextual dependencies and causal masking to model sequential dynamics. In the instruction tuning stage, we propose the Instruction-conditioned Q-Former (IQF), a query-based cross-attention transformer that injects instruction embeddings into EEG tokens and aligns them with textual label embeddings through learnable queries. We evaluate ELASTIQ on 20 datasets spanning motor imagery, emotion recognition, steady-state visual evoked potentials, covert speech, and healthcare tasks. ELASTIQ achieves state-of-the-art performance on 14 of the 20 datasets and obtains the best average results across all five task categories. Importantly, our analyses reveal for the first time that explicit task instructions serve as semantic priors guiding EEG embeddings into coherent and linguistically grounded spaces. The code and pre-trained weights will be released.

Problem

• Aligns EEG signals with language instructions for semantic guidance
• Enhances EEG decoding robustness and transferability across tasks
• Integrates task-aware embeddings to unify diverse BCI applications

Innovation

• Integrates task-aware semantic guidance for EEG embeddings
• Uses joint Spectral-Temporal Reconstruction in pretraining
• Employs Instruction-conditioned Q-Former for EEG-text alignment