MaDeL: Manifold-Decomposed Feature Losses for Generative Modeling

Excerpt

arXiv:2610.04419v1 Announce Type: cross Abstract: Generative models are often trained with isotropic objectives such as mean-squared error. For data concentrated near a low-dimensional manifold, however, such losses conflate displacement along the manifold, which may represent valid variation, with displacement away from it, which produces invalid samples. This mismatch is especially problematic in sparse, highly constrained domains, where ambient-space regression can encourage off-manifold inte