AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Saving Foundation Flow-Matching Priors for Inverse Problems

Yuxiang Wan, Ryan Devera, Wenjie Zhang, Ju Sun

ICML 2026 · Image generation › Fast diffusion sampling · approach: Flow matching distillation · 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
add time-dependent warm-start (ablation)FMPlug · DIV2K Gaussian deblurPSNR (dB): 25.1602 -> 26.0547Improved
add sharp Gaussianity regularization on top of warm-start (ablation)FMPlug · DIV2K Gaussian deblurPSNR (dB): 26.0547 -> 26.2563Improved
add sharp Gaussianity regularization on top of warm-start (ablation)FMPlug · DIV2K Gaussian deblurLPIPS: 0.4315 -> 0.4120Improved
use FMPlug instead of D-FlowD-Flow · AFHQ Gaussian deblurPSNR (dB): 25.90 -> 30.41Improved
use FMPlug instead of DIP on random inpaintingDIP · AFHQ 70% random inpaintingPSNR (dB): 33.32 -> 32.81Hurt
use FMPlug instead of FlowDPS-PFlowDPS-P · AFHQ 4x super-resolutionPSNR (dB): 28.75 -> 30.31Improved
use FMPlug with few-shot guidance instead of D-FlowD-Flow · InverseBench LISPSNR (dB): 19.67 -> 34.65Improved
use FMPlug instead of DIPDIP · InverseBench BKHPSNR (dB): 17.63 -> 22.91Improved
use foundation FM prior plus text prompt and inversion-seed strengthening techniquesFlowDPS and D-Flow · Gaussian deblurring AFHQ-CatqualityNo clear effect
set shell thickness epsilon to 0.025 (ablation)FMPlug · DIV2K Gaussian deblurPSNR (dB): 26.45 -> 26.58Improved
increase NFE from 1 to 5 (ablation)FMPlug · DIV2K Gaussian deblurPSNR (dB): 26.44 -> 26.62No clear effect
increase blur level sigma from 1 to 6 (ablation)FMPlug · DIV2K Gaussian deblurlearned warm-start time t*: 0.83 -> 0.72Hurt

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