Geometry-aware similarity metrics for neural representations on Riemannian and statistical manifolds

ArXi:2603.28764v1 Announce Type: cross Similarity measures are widely used to interpret the representational geometries used by neural networks to solve tasks. Yet, because existing methods compare the extrinsic geometry of representations in state space, rather than their intrinsic geometry, they may fail to capture subtle yet crucial distinctions between fundamentally different neural network solutions. Here, we