AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Quantifying Error Propagation and Model Collapse in Diffusion Models

Nail B. Khelifa, Richard E. Turner, Ramji Venkataramanan

ICML 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase fresh data fraction alpha from 0.1 to 0.9 in recursive training (ablation)recursively trained diffusion model · 10-dim Gaussian mixture, 20 generationsdrift from target distributionImproved
use moderate fresh data fraction alpha = 0.5 (ablation)recursively trained diffusion model · 10-dim Gaussian mixture, 20 generationsdrift from target distributionMixed
increase fresh data fraction alpha (ablation)recursive training, error memory · Gaussian mixture, accumulated divergence decompositioncontribution of past score errorsImproved
use state-dependent score perturbations instead of time-only perturbations (ablation)CIFAR-10 diffusion sampling · observability coefficient estimateobservability etaImproved
score error energy persists above a floor across generationsrecursive diffusion training (theory) · accumulated chi-squared divergenceaccumulated divergence D_NHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy