arXiv cs.CV
· Papers
Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models
arXiv:2510.05509v3 Announce Type: replace Abstract: 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 fait