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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add the retrieval module (ablation) | RAGAR · POG | personalization and semantic metrics | Improved |
| add rank rewards (ablation) | RAGAR · POG | personalization and semantic metrics | Improved |
| use retrieval number k=5 instead of k=0 (ablation) | RAGAR · POG | personalization and semantic metrics | Improved |
| increase retrieval k beyond 5 (ablation) | RAGAR · POG | personalization and semantic metrics | Hurt |
| increase noise samples r up to 5 (ablation) | RAGAR · POG | personalization and semantic metrics | Improved |
| use top-k retrieved history instead of random items (ablation) | user history construction · POG | CPIS/personalization metrics | Improved |
| use top-k retrieved history instead of rank k+1 to 2k items (ablation) | user history construction · POG | CPIS/personalization metrics | Improved |
| use RAGAR images instead of PMG images to train the recommender | MICRO · POG | Recall@10: 0.1804 -> 0.1927 | Improved |
| use RAGAR images instead of PMG images to train the recommender | MICRO · POG | NDCG@10: 0.1550 -> 0.1668 | Improved |
| use RAGAR images instead of PMG images to train the recommender | MICRO · ML-latest | Recall@10: 0.3213 -> 0.3299 | Improved |
| replace PMG with RAGAR in human evaluation | image generator · POG | personalization rank: 2.08 -> 1.66 | Improved |
| replace PMG with RAGAR | image generator · Sticker | ΔR: -0.73 -> 0.99 | Improved |
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.
- GLIDE — GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models (ICML 2022) · better on 3 of 3 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
- Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond (ICLR 2024 · similarity 0.88)
- AR-RAG: Autoregressive Retrieval Augmentation for Image Generation (NeurIPS 2025 · similarity 0.87)
- GenIR: Generative Visual Feedback for Mental Image Retrieval (NeurIPS 2025 · similarity 0.85)
- VisualLens: Personalization through Task-Agnostic Visual History (NeurIPS 2025 · similarity 0.85)
- JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation (CVPR 2024 · similarity 0.84)
- Retrieval-Augmented Perception: High-resolution Image Perception Meets Visual RAG (ICML 2025 · similarity 0.84)
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.
