DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG

ArXi:2605.18298v1 Announce Type: cross Foundation models pre-trained through masked reconstruction on large-scale EEG data have emerged as a promising paradigm for learning generalizable neural representations across diverse brain-computer interface applications. However, a critical yet overlooked challenge is that EEG encoders must learn representations invariant to incomplete observations-when different masked views of the same signal have minimal overlap, existing methods fail to constrain them to a consistent latent subspace, leading to degraded transferability.