AI RESEARCH
CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model
arXiv CS.LG
•
ArXi:2506.09110v3 Announce Type: replace Electroencephalography (EEG) provides real-time insights into brain activity and s diverse applications in neuroscience. While EEG foundation models (EFMs) have emerged to address the scalability issues of task-specific models, current approaches still yield clinically uninterpretable and weakly discriminative representations, inefficiently capturing global dependencies and neglecting important local neural events. We present CodeBrain, a two-stage EFM designed to fill this gap. In the first stage, we.