AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Diffusion Mental Averages

Phonphrm Thawatdamrongkit, Sukit Seripanitkarn, Supasorn Suwajanakorn

CVPR 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
align denoising trajectories of 1000 noise latents in h-space instead of averaging VAE latents or pixelsRealistic Vision v5.1 · Concept prototypesImageReward: 0.823 (D4M) -> 1.002Improved
DMA instead of D4M/MGD3 for run-to-run consistencyRealistic Vision v5.1 · Concept prototypesConsistency CLIP dist (lower better): 0.168 -> 0.031Improved
DMA instead of Avg VAE/GANgealing for representativenessRealistic Vision v5.1 · Concept prototypesRepresentativeness CLIP dist (lower better): 0.386 (GANgealing) -> 0.179Improved
Avg VAE and GANgealing versus DMA on consistencybaselines · Concept prototypesConsistency: 0 vs 0.031 (CLIP)Hurt
add LoRA or Textual Inversion cluster-specific conditioning to DMA for modes (ablation)DMA mode averages · Cluster prototypes (qualitative)semantic faithfulnessImproved
cluster modes before averaging instead of single overall average (ablation)DMA · Unsupervised modes (qualitative)mode coverageImproved

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