AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

WILD-Diffusion: A WDRO Inspired Training Method for Diffusion Models under Limited Data

Xianglu Wang, Wanlin Zhang, Hu Ding

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space

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
add WILD-DiffusionEDM-DDPM++ · CIFAR-10, 20% dataFID: 13.91 -> 12.14 (-12.72%)Improved
add WILD-DiffusionEDM-DDPM++ · CIFAR-10, 100% dataFID: 1.97 -> 1.93 (-2.03%)Improved
add WILD-DiffusionEDM-NCSN++ · FFHQ 64x64, 20% dataFID: 9.38 -> 7.89 (-15.88%)Improved
add WILD-DiffusionEDM-NCSN++ · FFHQ 64x64, 100% dataFID: 2.57 -> 2.54 (-1.16%)Improved
add WILD-DiffusionPatch Diffusion · CIFAR-10, 20% dataFID: 12.53 -> 11.78 (-5.99%)Improved
add WILD-DiffusionDeepCache · CIFAR-10, 20% dataFID: 15.33 -> 13.96 (-8.94%)Improved
add WILD-DiffusionEDM-ADM · LSUN-Church 256x256, 50% dataFID: 5.79 -> 5.13 (-11.40%)Improved
add WILD-Diffusion without pretrainingEDM-NCSN++ · 100-shot ObamaFID: 37.10 -> 34.52Improved
add WILD-Diffusion with pretrainingLD-Diffusion · 100-shot ObamaFID: 13.00 -> 12.54Improved
add WILD-Diffusion with pretrainingLD-Diffusion · AnimalFace CatFID: 12.77 -> 12.93No clear effect
increase interval m between WDRO sample updates (ablation)WILD-Diffusion · FFHQ 50% dataFIDHurt
increase number of inner steps K up to 5 (ablation)WILD-Diffusion · FFHQ 50% dataFIDImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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