AI Paper Atlas

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

Re-Align: Structured Reasoning-guided Alignment for In-Context Image Generation and Editing

Runze He, Yiji Cheng, Tiankai Hang, Zhimin Li, Yu Xu, Zijin Yin, Shiyi Zhang, Wenxun Dai, Penghui Du, Ao Ma, Chunyu Wang, Qinglin Lu and 2 more

CVPR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 8 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 SFT on Re-Align-410K with IC-CoT (ablation)BAGEL · OmniContext subsetOverall: 5.80 -> 6.77Improved
add reasoning-generation alignment (GRPO with CLIP surrogate reward) without diversity (ablation)Re-Align SFT · OmniContext subsetPrompt Following: 7.51 -> 7.46No clear effect
add reasoning-generation alignment (GRPO) (ablation)Re-Align SFT · OmniContext subsetCLIPout: 33.32 -> 33.50Improved
add reasoning-induced diversity to RGA (ablation)Re-Align SFT+RGA · OmniContext subsetOverall: 6.80 -> 6.89Improved
add reasoning-induced diversity to RGA (ablation)Re-Align SFT+RGA · OmniContext subsetPrompt Following: 7.46 -> 7.61Improved
use structured IC-CoT instead of no reasoning (ablation)Re-Align · GSB human evaluationwin rate: 20% higher win rateImproved
use structured IC-CoT instead of unstructured BAGEL-style CoT (ablation)Re-Align · GSB human evaluationwin rate: 16.25% higher win rateImproved
apply Re-Align training to BAGELBAGEL · OmniContext (average)Overall score: 5.73 -> 8.21Improved
apply Re-Align training to BAGELBAGEL · DreamOmni2Bench ReplaceOverall score: 1.37 -> 8.61Improved
compare Re-Align against Qwen-Image-Edit on single-subject generationRe-Align · OmniContext SINGLE (Character)Overall score: 8.35 -> 8.25Hurt
compare Re-Align against Emu3.5 and GPT-4o overallRe-Align · OmniContext (average)Overall score: 8.82/8.80 -> 8.21Hurt
Re-Align versus DreamOmni2 on Global editingDreamOmni2 · DreamOmni2Bench GlobalOverall score: 7.76 -> 7.85Improved

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