AI Paper Atlas

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

Interleaving Reasoning for Better Text-to-Image Generation

Wenxuan Huang, Shuang Chen, Zheyong Xie, Shaosheng Cao, SHIXIANG TANG, Yufan Shen, Qingyu Yin, Wenbo Hu, Xiaoman Wang, Yuntian Tang, Junbo Qiao, Hangyu Guo and 6 more

ICLR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 42 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 high-quality image data training to BAGEL w/ self-CoT (ablation)BAGEL w/ self-CoT · WISEoverall score: 0.70 -> 0.73Improved
add high-quality image training (ablation)BAGEL w/ self-CoT · GenAI-Benchoverall score: 0.81 -> 0.80No clear effect
train on full interleaving reasoning thinking-image trajectories (ablation)BAGEL w/ self-CoT + image training · WISEoverall score: 0.73 -> 0.76Improved
train on full interleaving reasoning thinking-image trajectories (ablation)BAGEL w/ self-CoT + image training · GenAI-Benchoverall score: 0.80 -> 0.83Improved
add decomposed learning modes with two-stage training (ablation)IRG · WISEoverall score: 0.76 -> 0.77Improved
add decomposed learning modes with two-stage training (ablation)IRG · TIIF testmini (short)overall score: 73.90 -> 76.00Improved
add reflection (second) turn to IRG (ablation)IRG · WISEoverall score: 0.79 -> 0.77No clear effect
add reflection (second) turn to IRG (ablation)IRG · WISE (MLLM judges)avg rank score: 36.7% -> 63.3%Improved
IRG vs BAGEL w/ self-CoTBAGEL · GenEvaloverall score: 0.79 -> 0.85Improved
IRG vs FLUX.1-dev on text renderingIRG · OneIG-ENtext rendering: 0.523 -> 0.377Hurt
IRG vs BAGEL w/ self-CoTBAGEL · OneIG-ENoverall score: 0.324 -> 0.415Improved

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