AI Paper Atlas

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

RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation

Run Ling, Wenji Wang, Yuting Liu, Guibing Guo, Haowei Liu, Jian Lu, Quanwei Zhang, Yexing Xu, Shuo Lu, Yun Wang, Yihua Shao, Linying Jiang and 1 more

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 0 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 the retrieval module (ablation)RAGAR · POGpersonalization and semantic metricsImproved
add rank rewards (ablation)RAGAR · POGpersonalization and semantic metricsImproved
use retrieval number k=5 instead of k=0 (ablation)RAGAR · POGpersonalization and semantic metricsImproved
increase retrieval k beyond 5 (ablation)RAGAR · POGpersonalization and semantic metricsHurt
increase noise samples r up to 5 (ablation)RAGAR · POGpersonalization and semantic metricsImproved
use top-k retrieved history instead of random items (ablation)user history construction · POGCPIS/personalization metricsImproved
use top-k retrieved history instead of rank k+1 to 2k items (ablation)user history construction · POGCPIS/personalization metricsImproved
use RAGAR images instead of PMG images to train the recommenderMICRO · POGRecall@10: 0.1804 -> 0.1927Improved
use RAGAR images instead of PMG images to train the recommenderMICRO · POGNDCG@10: 0.1550 -> 0.1668Improved
use RAGAR images instead of PMG images to train the recommenderMICRO · ML-latestRecall@10: 0.3213 -> 0.3299Improved
replace PMG with RAGAR in human evaluationimage generator · POGpersonalization rank: 2.08 -> 1.66Improved
replace PMG with RAGARimage generator · StickerΔR: -0.73 -> 0.99Improved

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