AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss

Yucheng Zhou, Hao Li, Jianbing Shen

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 2 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 OT-based condition refinement (Wasserstein gradient flow) to autoregressive diffusion-loss model (ablation)Baseline (AR) · ImageNet 256x256FID: 2.02 -> 1.52Improved
add OT-based condition refinement to MARMAR 943M · ImageNet 256x256FID: 1.55 -> 1.31Improved
add OT-based condition refinement to MAR (ablation)MAR 208M · ImageNet 256x256FID: 2.31 -> 1.96Improved
add OT-based condition refinement to MAR (ablation)MAR 479M · ImageNet 256x256FID: 1.78 -> 1.59Improved
add OT-based condition refinement to MAR at higher resolutionMAR ~481M · ImageNet 512x512FID: 1.73 -> 1.58Improved
use autoregressive condition generation instead of static conditional diffusion (ablation)conditional diffusion baseline · ImageNet 256x256FID: 3.26 -> 2.02Improved
compare Ours (AR) with De-MAR and RAROurs (AR) · ImageNet 256x256FID: 1.52 vs De-MAR 1.47, RAR 1.50Mixed
add OT condition refinementdenoising process · ImageNet 256x256SNR during denoisingImproved

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