AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

One-step Optimal Transport via Regularized Distribution Matching Distillation

Denis Rakitin, Ivan Shchekotov, Viacheslav Meshchaninov, Dmitry Vetrov

ICML 2026 · Image generation › Fast diffusion sampling · approach: Flow matching distillation

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 LPIPS instead of L2 as transport cost (ablation)RDMD · AFHQv2 64x64 Wild->CatFID: 17.31 -> 17.17No clear effect
use LPIPS instead of L2 as transport cost (ablation)RDMD · AFHQv2 64x64 Wild->CatL2: 14.71 -> 19.49Hurt
use LPIPS instead of L2 cost for color inversion task (ablation)RDMD · Inverted-MNIST to MNISTsemantic correctnessImproved
replace adversarial OT training with diffusion distribution matching (RDMD vs DIOTM)OT translation · CelebA 64x64 M2F (5k samples)FID: 31.34 -> 20.99Improved
replace adversarial OT training with RDMD (vs ASBM)OT translation · CelebA 64x64 M2F (5k samples)FID: 43.97 -> 20.99Improved
reduce training data to 5k samples (RDMD)RDMD · CelebA 64x64 M2FFID: 10.36 -> 20.99Hurt
reduce training data to 5k samples (ASBM)ASBM · CelebA 64x64 M2FFID: 23.06 -> 43.97Hurt
reduce training data to 5k samples (DIOTM)DIOTM · CelebA 64x64 M2FFID: 15.81 -> 31.34Hurt
RDMD vs strongest OT baseline DIOTMone-step translation · AFHQv2 64x64 Wild->CatLPIPS: 0.417 -> 0.352Improved
RDMD vs DDIB on realismtranslation · CelebA 128x128 Male->FemaleFID: 5.39 -> 9.30Hurt
RDMD vs EGSDE† at 256x256translation · AFHQv2 256x256 Cat->DogFID: 51.04 -> 44.32Improved
RDMD vs EGSDE† at 256x256translation · AFHQv2 256x256 Cat->DogL2: 62.06 -> 64.44Hurt

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