Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models

ArXi:2510.05509v2 Announce Type: replace Diffusion models are powerful deep generative models, but unlike classical models, they lack an explicit low-dimensional latent space that parameterizes the data manifold. This absence makes it difficult to perform manifold-aware operations, such as geometrically faithful interpolation or conditional guidance that respects the learned manifold. We propose a