AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs

Hongkang Li, Hancheng Min, Rene Vidal

ICML 2026 · Image generation › Fast diffusion sampling · approach: Denoising diffusion probabilistic models · 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
increase the number of distinct patterns K per data point (ablation)one-layer transformer denoiser on synthetic MTGM data · synthetic MTGM (d=64, M=8, P=256)training iterations to convergeHurt
make the pattern distribution more uniform (larger minimal mixture fraction) (ablation)one-layer transformer denoiser on synthetic MTGM data · synthetic MTGMiterations to converge (excess risk)Improved
sample diffusion time steps only from the first 40% (higher time-averaged SNR) (ablation)one-layer transformer denoiser on synthetic MTGM data · synthetic MTGMconvergence speed (excess risk)Improved
increase tokens per data point Ptrained transformer attention · theory, MTGM dataerror in estimating mean patternImproved
train transformer with DDPM lossone-layer single-head transformer · synthetic MTGMDDPM test loss vs Bayes riskImproved
train transformer with DDPM lossone-layer single-head transformer · synthetic MTGMattention weight on same-pattern keysImproved
use fewer training samples for minority class (30% of digit 2) (ablation)6-layer 4-head DiT · MNIST digits 0-3FID of generated digitHurt

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