{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:17:35Z","timestamp":1777889855816,"version":"3.51.4"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62422606,62201484,624B2124"],"award-info":[{"award-number":["62422606,62201484,624B2124"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01758","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18917-18926","source":"Crossref","is-referenced-by-count":0,"title":["DiffDoctor: Diagnosing Image Diffusion Models Before Treating"],"prefix":"10.1109","author":[{"given":"Yiyang","family":"Wang","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaogang","family":"Xu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sihui","family":"Ji","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Tongyi Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Hands xl.","year":"2024"},{"key":"ref2","volume-title":"Qwen technical report.","author":"Bai","year":"2023"},{"key":"ref3","volume-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond.","author":"Bai","year":"2023"},{"key":"ref4","article-title":"Training diffusion models with reinforcement learning","volume-title":"ICLR","author":"Black","year":"2024"},{"key":"ref5","volume-title":"Synartifact: Classifying and alleviating artifacts in synthetic images via vision-language model.","author":"Cao","year":"2024"},{"key":"ref6","article-title":"Directly fine-tuning diffusion models on differentiable rewards","volume-title":"ICLR","author":"Clark","year":"2024"},{"key":"ref7","volume-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref8","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","volume-title":"NeurIPS","author":"Fan","year":"2024"},{"key":"ref9","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref10","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref12","volume-title":"Black Forest Labs. Flux.1.","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01835"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref15","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"ICLR","author":"Liu","year":"2023"},{"key":"ref16","article-title":"Training language models to follow instructions with human feedback","volume-title":"NeurIPS","author":"Ouyang","year":"2022"},{"key":"ref17","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref18","volume-title":"Aligning text-to-image diffusion models with reward backpropagation.","author":"Prabhudesai","year":"2023"},{"key":"ref19","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"NeurIPS","author":"Rafailov","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref22","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"NeurIPS","author":"Schuhmann","year":"2022"},{"key":"ref23","volume-title":"Proximal policy optimization algorithms.","author":"Schulman","year":"2017"},{"key":"ref24","article-title":"Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","author":"Team","year":"2024","journal-title":"arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01017"},{"key":"ref27","article-title":"Human preference score v 2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv"},{"key":"ref28","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume-title":"NeurIPS","author":"Xie","year":"2021"},{"key":"ref29","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"NeurIPS","author":"Xu","year":"2024"},{"key":"ref30","volume-title":"Fakeshield: Explainable image forgery detection and localization via multi-modal large language models.","author":"Xu","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00699"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref34","article-title":"Depth anything v2","volume-title":"NeurIPS","author":"Yang","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01213"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00697"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_1"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445847.pdf?arnumber=11445847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:22:21Z","timestamp":1777612941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01758","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}