Decoding Dynamic Visual Experience from Calcium Imaging via Cell-Pattern-Aware Pretraining

ArXi:2510.18516v3 Announce Type: replace-cross Neural recordings exhibit a distinctive form of heterogeneity rooted in differences in cell types, intrinsic circuit dynamics, and stochastic stimulus-response variability that goes beyond ordinary dataset variability, mixing statistically regular neurons with highly stochastic, stimulus-contingent ones within the same dataset. This heterogeneity poses a challenge for self-supervised learning (SSL) -- learnable statistical regularity -- thereby destabilizing representation learning and limiting reliable scaling. We.