EEG-X: Device-Agnostic and Noise-Robust Foundation Model for EEG

The introduction of EEG-X marks a significant advancement in EEG analysis, tackling two major challenges: dataset variability and low signal-to-noise ratios. Traditional EEG models often struggle with these issues, leading to less reliable outcomes. EEG-X overcomes these hurdles by employing a device-agnostic framework and a noise-aware masking and reconstruction strategy. This model utilizes a location-based channel embedding to improve generalization across different devices and recording conditions. Furthermore, EEG-X is trained to reconstruct denoised signals, focusing on neural activity rather than noise, which enhances its robustness. Experiments conducted on diverse datasets demonstrate the effectiveness of EEG-X, paving the way for more accurate EEG representation learning and broader applications in neuroscience and clinical settings.