Eero P Simoncelli

Learning a distance measure from the information-estimation geometry of data

Modeling Visual Cortex by Maximizing Layerwise Multiscale Manifold Capacity

Unconditional CNN denoisers contain sparse semantic representations of images

Unsupervised learning of disentangled representations via diffusion variational autoencoders

Learning normalized image densities via dual score matching

Discriminating image representations with principal distortions

Feature-guided score diffusion for sampling conditional densities