AI Paper Atlas

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

Self-Corrected Image Generation with Explainable Latent Rewards

Yinyi Luo, Hrishikesh Gokhale, Marios Savvides, Jindong Wang, Shengfeng He

CVPR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 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 RL objective (CLIPScore reward) (ablation)xLARD · GenEvaloverall (%): 77.68 -> 78.78Improved
swap CLIPScore reward for Sentence-BERT reward (ablation)xLARD · GenEvaloverall (%): 78.78 -> 78.42No clear effect
add confidence-guided latent modulation (ablation)xLARD · GenEvaloverall: -3.3% GenEval drop when removedImproved
add latent anchor (ablation)xLARD · GenEvaloverall (%): 76.90 (without anchor)Improved
add counting reward (ablation)xLARD · GenEvaloverall (%): 76.45 -> 81.24Improved
add color reward (ablation)xLARD · GenEvaloverall (%): 78.92 -> 81.24Improved
add position reward (ablation)xLARD · GenEvaloverall (%): 79.15 -> 81.24Improved
add counting reward (ablation)xLARD · DPG-Benchoverall (%): 83.10 -> 86.72Improved
add color reward (ablation)xLARD · DPG-Benchoverall (%): 84.55 -> 86.72Improved
add xLARD corrector to OmniGen2OmniGen2 · GenEvaloverall (%): 77.03 -> 81.29Improved
add xLARD corrector to BAGELBAGEL · GenEvaloverall (%): 78.97 -> 81.38Improved
add xLARD corrector to Show-OShow-O · GenEvaloverall (%): 68.05 -> 74.89Improved

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