AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

On the Design of One-step Diffusion via Shortcutting Flow Paths

Haitao Lin, Peiyan Hu, Minsi Ren, Zhifeng Gao, Zhi-Ming Ma, Guolin Ke, Tailin Wu, Stan Z. Li

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 3 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
use ESC improvements instead of MeanFlow baseline (240 epochs, 1-NFE)MeanFlow SiT-XL/2 · ImageNet-256 (1-NFE, CFG)FID50k: 3.43 -> 2.85Improved
train ESC for 480 epochs instead of 240ESC SiT-XL/2 · ImageNet-256 (1-NFE, CFG)FID50k: 2.85 -> 2.53Improved
use plug-in velocity (minibatch mixture) instead of conditional velocity (ablation)continuous-time shortcut model · ImageNet-256 training costtime per iteration (ms): 554 -> 558 ms/iterNo clear effect
add class-consistent mini-batching under CFG training (ablation)ESC · ImageNet-256FID50k finalNo clear effect
add class-consistent mini-batching under CFG training (ablation)ESC · ImageNet-256FID50k convergence speedImproved
use linear paths instead of cosine paths (ablation)CT and sCT shortcut models · CIFAR-10 / ImageNet-256FID50kImproved
use continuous-time instead of discrete-time shortcut models (ablation)CT and SCD · CIFAR-10 (unconditional)FID50kImproved
sample terminal time r randomly instead of fixing r=0 (ablation)sCT-linear vs MeanFlow · CIFAR-10 / ImageNet-256FID50kMixed
add gradual time sampler from sCT to MeanFlow, K_fix0 about 20k (ablation)MeanFlow · ImageNet-256 SiT-B/2FID50kImproved
add variational adaptive loss weighting and tangent warmup (ablation)continuous-time shortcut model · CIFAR-10 / ImageNet-256FID50kImproved

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