{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:46:11Z","timestamp":1781883971199,"version":"3.54.5"},"reference-count":78,"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":["62206272"],"award-info":[{"award-number":["62206272"]}],"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\/iccv51701.2025.01763","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18969-18979","source":"Crossref","is-referenced-by-count":2,"title":["VisualCloze: A Universal Image Generation Framework via Visual in-Context Learning"],"prefix":"10.1109","author":[{"given":"Zhong-Yu","family":"Li","sequence":"first","affiliation":[{"name":"NKIARI, Shenzhen Futian"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoyi","family":"Du","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juncheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"NKIARI, Shenzhen Futian"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Building normalizing flows with stochastic interpolants","author":"Albergo","year":"2023","journal-title":"ICLR"},{"key":"ref3","article-title":"Towards in-context scene understanding","author":"Balazevic","year":"2023","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1813"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2929257"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01166"},{"key":"ref9","first-page":"2","article-title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","author":"Chen","year":"2018","journal-title":"ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref11","first-page":"1","article-title":"CatVTON: Concatenation is all you need for virtual try-on with diffusion models","author":"Chong","year":"2025","journal-title":"ICLR"},{"key":"ref12","first-page":"3","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref14","author":"Esser","year":"2024","journal-title":"Scaling rectified flow transformers for high-resolution image synthesis"},{"key":"ref15","first-page":"2","article-title":"Efficiently identifying task groupings for multi-task learning","author":"Fifty","year":"2021","journal-title":"NeurIPS"},{"key":"ref16","first-page":"3","author":"Gao","year":"2024","journal-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02117"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19953"},{"key":"ref20","first-page":"3","volume-title":"Algorithms for rendering in artistic styles","author":"Hertzmann","year":"2001"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383295"},{"key":"ref22","first-page":"6","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref23","first-page":"3","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref24","first-page":"6","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref25","first-page":"3","author":"Huang","year":"2024","journal-title":"Group diffusion transformers are unsupervised multitask learners"},{"key":"ref26","author":"Huang","year":"2024","journal-title":"In-context lora for diffusion transformers"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref28","first-page":"2","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"Kendall","year":"2018","journal-title":"CVPR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"ref30","volume-title":"Black Forest Labs","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01710"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00255"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref35","author":"Lin","year":"2024","journal-title":"Pixwizard: Versatile image-to-image visual assistant with open-language instructions"},{"key":"ref36","first-page":"3","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023","journal-title":"ICLR"},{"key":"ref37","first-page":"3","author":"Liu","year":"2024","journal-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining"},{"key":"ref38","first-page":"3","author":"Liu","year":"2022","journal-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow"},{"key":"ref39","author":"Liu","year":"2023","journal-title":"Unifying image processing as visual prompting question answering"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00207"},{"key":"ref41","first-page":"6","author":"Meng","year":"2021","journal-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations"},{"key":"ref42","first-page":"7","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref45","first-page":"4","author":"Ravi","year":"2024","journal-title":"Sam 2: Segment anything in images and videos"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref47","first-page":"2","author":"Ruder","year":"2017","journal-title":"An overview of multi-task learning in deep neural networks"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01269"},{"key":"ref50","first-page":"3","author":"Sun","year":"2024","journal-title":"Autoregressive model beats diffusion: Llama for scalable image generation"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3554410"},{"key":"ref52","article-title":"Imagebrush: Learning visual in-context instructions for exemplarbased image manipulation","author":"Yasheng","year":"2023","journal-title":"NeurIPS"},{"key":"ref53","author":"Tan","year":"2024","journal-title":"Ominicontrol: Minimal and universal control for diffusion transformer"},{"key":"ref54","first-page":"3","article-title":"Leveraging visual tokens for extended text contexts in multi-modal learning","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref55","author":"Wang","year":"2024","journal-title":"Instantstyle-plus: Style transfer with content-preserving in text-to-image generation"},{"key":"ref56","first-page":"4","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"ref59","first-page":"3","article-title":"In-context learning unlocked for diffusion models","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref60","author":"Wei","year":"2024","journal-title":"Omniedit: Building image editing generalist models through specialist supervision"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01241"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"ref64","first-page":"4","author":"Yang","year":"2024","journal-title":"Depth anything v2"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"ref66","first-page":"2","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"ref68","first-page":"3","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01553"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref72","article-title":"What makes good examples for visual in-context learning?","author":"Zhang","year":"2023","journal-title":"NeurIPS"},{"key":"ref73","first-page":"3","author":"Zhao","year":"2025","journal-title":"Diception: A generalist diffusion model for visual perceptual tasks"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.26599\/AIR.2024.9150038"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.940"},{"key":"ref77","article-title":"Unleashing the potential of the diffusion model in few-shot semantic segmentation","author":"Zhu","year":"2024","journal-title":"NeurIPS"},{"key":"ref78","article-title":"Lumina-next: Making lumina-t2x stronger and faster with next-dit","author":"Zhuo","year":"2024","journal-title":"NeurIPS"}],"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\/11444301.pdf?arnumber=11444301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:35:24Z","timestamp":1777530924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01763","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}