{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:10Z","timestamp":1777865410480,"version":"3.51.4"},"reference-count":53,"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\/501100002551","name":"Seoul National University","doi-asserted-by":"publisher","award":["RS-2025-02305581,RS2021II211343"],"award-info":[{"award-number":["RS-2025-02305581,RS2021II211343"]}],"id":[{"id":"10.13039\/501100002551","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008903","name":"Ministry of Health & Welfare","doi-asserted-by":"publisher","award":["RS-2025-02307233"],"award-info":[{"award-number":["RS-2025-02307233"]}],"id":[{"id":"10.13039\/100008903","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2023-00209060"],"award-info":[{"award-number":["RS-2023-00209060"]}],"id":[{"id":"10.13039\/501100003725","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\/iccv51701.2025.01751","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18844-18854","source":"Crossref","is-referenced-by-count":0,"title":["Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing"],"prefix":"10.1109","author":[{"given":"Joowon","family":"Kim","sequence":"first","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziseok","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghyeon","family":"Cho","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanghyun","family":"Jo","sequence":"additional","affiliation":[{"name":"OGQ"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeonsung","family":"Jung","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungsu","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunho","family":"Yang","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681047"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00683"},{"key":"ref6","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Fortyfirst International Conference on Machine Learning","author":"Esser"},{"key":"ref7","article-title":"Guiding instruction-based image editing via multimodal large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Fu"},{"key":"ref8","volume-title":"Seed-data-edit technical report: A hybrid dataset for instructional image editing","author":"Ge","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00667"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref12","article-title":"Can we generate images with cot? let\u2019s verify and reinforce image generation step by step","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref13","volume-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref14","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01185"},{"key":"ref18","volume-title":"Hq-edit: A high-quality dataset for instruction-based image editing","author":"Hui","year":"2024"},{"key":"ref19","article-title":"Pnp inversion: Boosting diffusion-based editing with 3 lines of code","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ju"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_6"},{"key":"ref21","article-title":"Imagenhub: Standardizing the evaluation of conditional image generation models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ku"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.663"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_23"},{"key":"ref24","volume-title":"Moecontroller: Instruction-based arbitrary image manipulation with mixture-of-expert controllers","author":"Li","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00598"},{"key":"ref26","article-title":"Reinforcement learning with human feedback: Learning dynamic choices via pessimism","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref28","article-title":"Inference-time scaling for diffusion models beyond scaling denoising steps","author":"Ma","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612191"},{"key":"ref30","article-title":"Semanticdriven initial image construction for guided image synthesis in diffusion model","author":"Mao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref33","first-page":"37097","article-title":"Diffusion rejection sampling","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Na"},{"key":"ref34","volume-title":"Introducing gpt-4o: our fastest and most affordable flagship model","year":"2024"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"ref38","article-title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters","author":"Snell","year":"2024","journal-title":"arXiv"},{"key":"ref39","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref41","first-page":"32630","article-title":"Fast best-of-n decoding via speculative rejection","volume":"37","author":"Sun","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","article-title":"Postedit: Posterior sampling for efficient zero-shot image editing","author":"Tian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref44","article-title":"Dialogpaint: A dialog-based image editing model","author":"Wei","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00299"},{"key":"ref46","volume-title":"Inversion-free image editing with natural language","author":"Xu","year":"2024"},{"key":"ref47","article-title":"Task-oriented diffusion inversion for high-fidelity text-based editing","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref48","volume-title":"Editworld: Simulating world dynamics for instruction-following image editing","author":"Yang","year":"2024"},{"issue":"1","key":"ref49","first-page":"1","article-title":"The dawn of 1mms: Preliminary explorations with gpt-4v (ision)","volume":"9","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00862"},{"key":"ref53","article-title":"Ultraedit: Instruction-based fine-grained image editing at scale","volume-title":"The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Zhao"}],"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\/11445670.pdf?arnumber=11445670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:28:16Z","timestamp":1777530496000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445670\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01751","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}