Dimensional Coactivation for Representational Consistency in Frozen Vision Foundation Models

ArXi:2605.08249v1 Announce Type: new Frozen vision foundation models do not merely extract features; they organize images through a learned coordinate system. We ask whether that coordinate system remains internally coherent within a single input. This leads to Representational Consistency: the study of whether a frozen foundation model represents one sample coherently across its semantic subregions. We