Tootfinder

Optimal Stopping in Latent Diffusion Models
Yu-Han Wu, Quentin Berthet, G\'erard Biau, Claire Boyer, Romuald Elie, Pierre Marion
https://arxiv.org/abs/2510.08409 https://

Optimal Stopping in Latent Diffusion Models
We identify and analyze a surprising phenomenon of Latent Diffusion Models (LDMs) where the final steps of the diffusion can degrade sample quality. In contrast to conventional arguments that justify early stopping for numerical stability, this phenomenon is intrinsic to the dimensionality reduction in LDMs. We provide a principled explanation by analyzing the interaction between latent dimension and stopping time. Under a Gaussian framework with linear autoencoders, we characterize the conditi…