BrainPro: Process-conditioned Pretraining with Topographic Retrieval for Large EEG Models
BrainPro is a large EEG foundation model designed to handle varied electrode layouts and process-related mental states. It achieves this by using retrieval-based spatial learning to map different montages onto a universal template and employing a brain-state decoupling module. This allows the model to learn shared general EEG features alongside distinct, state-specific representations, leading to strong performance across various BCI benchmarks.