AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance

Matina Mahdizadeh Sani, Nima Jamali, Mohammad Jalali, Farzan Farnia

ICML 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 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 MMD guidance to unguided LDMLDM · FFHQ sunglasses userFD: 1220.5 -> 693.0Improved
add MMD guidance to unguided LDMLDM · FFHQ reading-glasses userFD: 702.9 -> 574.3Improved
use MMD guidance instead of Domain GuidanceLDM · FFHQ sunglasses userFD: 710.6 -> 693.0Improved
use classifier guidance instead of no guidanceLDM · FFHQ sunglasses userFD: 1220.5 -> 1195.9No clear effect
add MMD guidance with product kernelSDXL · Prompt-aware style datasetFD: 1953.8 -> 1674.4Improved
add MMD guidance with product kernelPixArt · Prompt-aware style datasetFD: 1358.4 -> 1060.6Improved
add MMD guidance (runtime overhead)SDXL · Runtime, 500 samplescumulative time: 3142 -> 3447Hurt
increase reference samples from 10 to 200 (ablation)MMD Guidance · Prompt-aware style datasetFD: 1805.92 -> 1674.45Improved
increase reference samples from 10 to 100 (ablation)MMD Guidance · GMM large gap (r=20)FD: 123.22 -> 108.61Improved
increase reference samples from 10 to 100 (ablation)MMD Guidance · GMM shifted targetFD: 0.60 -> 0.03Improved
keep the intra-batch diversity term (ablation)MMD Guidance · synthetic GMM and FFHQmode coverageImproved

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