AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

STORK: Faster Diffusion and Flow Matching Sampling by Resolving both Stiffness and Structure-Dependence

Zheng Tan, Weizhen Wang, Andrea L. Bertozzi, Ernest K. Ryu

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Flow matching distillation · 6 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
add Taylor-approximated virtual NFEs to stabilized RK4 (ablation)SRK4 · CIFAR-10 NFE 10FID: 443.812 -> 5.497Improved
use STORK-4 instead of classical RK4 (ablation)RK4 · CIFAR-10 NFE 20FID: 33.662 -> 4.167Improved
use sub-steps s=9 instead of s=5 (ablation)STORK-4 SANA-0.6B · MJHQ-30K NFE 9FID: 8.537 -> 6.526Improved
increase sub-steps from s=9 to s=104 (ablation)STORK-4 SANA-0.6B · MJHQ-30K NFE 9FID: 6.526 -> 7.412Hurt
raise Taylor order from 1st to 2nd (ablation)STORK-4 · MJHQ-30K NFE 7FID: 7.659 -> 54.179Hurt
raise Taylor order from 1st to 3rd (ablation)STORK-4 · MJHQ-30K NFE 9FID: 6.526 -> 12.556Hurt
raise solver order from STORK-1 to STORK-4 (1st-order Taylor) (ablation)STORK · MJHQ-30K NFE 9FID: 20.799 -> 6.526Improved
raise solver order from STORK-2 to STORK-4 (1st-order Taylor) (ablation)STORK · MJHQ-30K NFE 9FID: 7.417 -> 6.526Improved
use STORK-4 instead of DPM-Solver++DPM-Solver++ · CIFAR-10 NFE 10FID: 6.471 -> 5.497Improved
use STORK-4 instead of UniPCUniPC · LSUN-Bedroom NFE 10FID: 12.146 -> 9.594Improved
use STORK instead of Flow-UniPCFlow-UniPC Hunyuan · EvalCrafter NFE 4final score: 206 -> 210Improved
use STORK instead of Flow-DPM-Solver++Flow-DPM-Solver++ Hunyuan · EvalCrafter NFE 8final score: 216 -> 216No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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