DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting

TL;DR

DECODE introduces a novel diffusion-based framework that combines natural language guidance with historical EEG data to accurately forecast event-specific neural responses, enhancing interpretability and zero-shot generalization in BCI applications.

Contribution

The paper presents DECODE, a new method that unifies semantic language cues with temporal EEG dynamics using diffusion models, enabling accurate, interpretable, and generalizable neural signal prediction.

Findings

Achieves sub-microvolt MAE of 0.626 microvolt over 75 timesteps

Demonstrates effective zero-shot generalization to unseen behaviors

Provides well-calibrated uncertainty estimates for EEG predictions

Abstract

Forecasting Electroncephalography (EEG) signals during cognitive events remains a fundamental challenge in neuroscience and Brain-Computer Interfaces (BCIs), as existing methods struggle to capture both the stochastic nature of neural dynamics and the semantic context of behavioral tasks. We present the Dual-Enhanced COnditioned Diffusion (DECODE) for EEG, a novel framework that unifies semantic guidance from natural language descriptions with temporal dynamics from historical signals to generate event-specific neural responses. DECODE leverages pre-trained language models to condition the diffusion process on rich textual descriptions of cognitive events, while maintaining temporal coherence through history-based Langevin dynamics. Evaluated on a real-world driving task dataset with five distinct behaviors, DECODE achieves sub-microvolt prediction accuracy (MAE = 0.626 microvolt) over 75 timestep horizons while maintaining well-calibrated uncertainty estimates. Our framework demonstrates that natural language can effectively bridge high-level cognitive descriptions and low-level neural dynamics, opening new possibilities for zero-shot generalization to novel behaviors and interpretable BCIs. By generating physiologically plausible, event-specific EEG trajectories conditioned on semantic descriptions, DECODE establishes a new paradigm for understanding and predicting context-dependent neural activity.