AI Paper Atlas

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

Scaling Multi-Reference Image Generation with Dynamic Reward Optimization

Wenwang Huang, Yusen Fu, Mengfei Huang, Junjie Wang, Yulin Li, Gan Liu, Jing Cai, Yancheng He, Zhuotao Tian

ECCV 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 CSD style reward (ablation)DyRef on Qwen-Image-Edit-2511 · OmniRef-Bench objective stylestyle score: 0.36 -> 0.46Improved
add CSD style reward (ablation)DyRef on Qwen-Image-Edit-2511 · OmniRef-Bench MLLM stylestyle score: 6.33 -> 8.67Improved
add DAR (difficulty-aware advantage reweighting) over standard GRPO (ablation)DyRef on Qwen-Image-Edit-2511 · OmniRef-Bench objective averageaverage score: 0.69 -> 0.71Improved
add DAR over standard GRPO (ablation)DyRef on Qwen-Image-Edit-2511 · OmniRef-Bench MLLM averageaverage score: 8.03 -> 8.38Improved
add DRS (discriminative reward scaling) (ablation)DyRef on Qwen-Image-Edit-2511 · OmniRef-Bench MLLM stylestyle score: 8.12 -> 8.67Improved
add DRS (discriminative reward scaling) (ablation)DyRef on Qwen-Image-Edit-2511 · OmniRef-Bench objective averageaverage score: 0.71 -> 0.71No clear effect
add DRS (ablation)DyRef on Qwen-Image-Edit-2511 · OmniRef-Bench MLLM aestheticsAes score: 8.03 -> 8.14Improved
apply DyRef to Qwen-Image-Edit-2511Qwen-Image-Edit-2511 · OmniRef-Bench MLLM averageaverage score: 4.97 -> 8.38Improved
apply DyRef to FLUX.2 [klein] 9BFLUX.2 [klein] · OmniRef-Bench MLLM averageaverage score: 6.49 -> 8.03Improved
apply DyRef to Qwen-Image-Edit-2511Qwen-Image-Edit-2511 · ImgEditoverall score: 4.07 -> 4.32Improved
apply DyRef to FLUX.2 [klein]FLUX.2 [klein] · ImgEditoverall score: 4.07 -> 4.11No clear effect
apply DyRef to Qwen-Image-Edit-2511Qwen-Image-Edit-2511 · DreamBench++CP*PF: 0.53 -> 0.62Improved

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