The paper reinterprets as a family of deterministic dynamical systems, one per noise scale. At each fixed scale, iterating the denoiser on its own output yields attractors that correspond to modes of the smoothed data density. The key insight is that memorized examples—due to duplication, overfitting, or outliers—persist as attractors up to larger noise scales than ordinary examples. This persistence is quantified by the critical scale σ_c, which measures the largest noise level at which an example remains an attractor. Experiments on CIFAR-10 and Stable Diffusion show that σ_c detects memorization and is interpretable, revealing properties like caption vs. image contributions and spatial localization of memorized content.
Memorization in diffusion models measured by persistence across noise scales
The authors define a critical noise scale that detects duplicated, overfitted, and outlier examples in trained models.
Top University
Cristina López Amado · Marco Fumero · Francesco Locatello
Institute of Science and Technology Austria (ISTA)
Research Digest··2 min read
In one line
Diffusion models' fixed-scale denoiser dynamics reveal memorization through a critical noise scale.
Before you read this
An idea this paper builds onRead it as
López Amado et al. reinterpret diffusion models as families of deterministic dynamical systems indexed by noise level.
The authors treat each denoiser D_σ of a as a self-map x_{k+1}=D_σ(x_k).
How it works
stage by stageThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.