What masking geometry works best for EEG foundation models?
This paper formalizes the design choices for spatio-temporal masking strategies and train various models with a single pipeline under varying masking configurations across two SSL frameworks (MAE and JEPA), and systematically evaluates the resulting 58 pre-trained models under a linear probe.
Pierre Guetschel, B. Aristimunha, Y. El Ouahidi et al.
· 0 citations