AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Progress by Pieces: Test-Time Scaling for Autoregressive Image Generation

Joonhyung Park, Hyeongwon Jang, Joowon Kim, Eunho Yang

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 1 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
replace Best-of-N with GridAR grid-partitioned progressive generation (N=4 vs N=8)Janus-Pro-7B · T2I-CompBench++average score: 14.4% higher than Best-of-N (N=8) with 25.6% less wall-clock timeImproved
apply GridAR to LlamaGen at same NLlamaGen · T2I-CompBench++average score: 4.9%Improved
replace Best-of-N (N=8) with GridAR (N=8) on LlamaGen color attributionLlamaGen · GenEval Color Attributionscore: 0.14 -> 0.13No clear effect
add GridAR to EditAR instead of Best-of-N (N=4)EditAR · PIE-Benchstructure distance and MSE: -10.54% structure distance, -26.07% MSEImproved
GridAR (N=4) vs Best-of-N (N=8) on instruction fidelity in editingEditAR · PIE-BenchCLIP similarity: 25.532 vs 25.628No clear effect
add mid-generation layout-specified prompt reformulation (ablation)GridAR (N=4) Janus-Pro · T2I-CompBench++average score: 0.4764 -> 0.5654Improved
reformulate prompt at the start with a planner instead of midway from partial images (ablation)GridAR (N=4) Janus-Pro · T2I-CompBench++average score: 0.5654 -> 0.5027Hurt
swap GPT-4.1 verifier for GPT-4o-mini (ablation)GridAR (N=4) · T2I-CompBench++improvement over Best-of-N: 18.5% improvementNo clear effect
swap GPT-4.1 verifier for open-source MiniCPM-V 4.5 (ablation)GridAR (N=4) · T2I-CompBench++improvement over Best-of-N: 15.8%No clear effect
use verification step in GridAR rather than plain Best-of-N samplingGridAR (N=4) · Janus-Pro wall-clock timeseconds: 23.9s -> 36.5s (vs Best-of-N N=4)Hurt
reject only infeasible candidates instead of top-k selection (ablation)GridAR · candidate pool diversitydesign rationaleImproved

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