<ul><li>Study evaluates the efficacy of Large EEG Models (LEMs) by fine-tuning LaBraM on a real-world stress classification dataset from a graduate classroom.</li><li>Best-performing fine-tuned model achieves a balanced accuracy of 90.47% in distinguishing between normal and elevated stress states using resting-state EEG data.</li><li>The fine-tuned LEM outperforms traditional stress classifiers in accuracy and inference efficiency.</li><li>Results show LEMs' potential to process real-world EEG data effectively and revolutionize brain-computer interface applications with a data-centric design approach.</li></ul>

From Theory to Application: Fine-Tuning Large EEG Model with Real-World Stress Data

Discover more