{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:09:27Z","timestamp":1777889367609,"version":"3.51.4"},"reference-count":62,"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":"NSFC","doi-asserted-by":"publisher","award":["62225604"],"award-info":[{"award-number":["62225604"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100003536","name":"Youth Foundation","doi-asserted-by":"publisher","award":["62202243"],"award-info":[{"award-number":["62202243"]}],"id":[{"id":"10.13039\/100003536","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002924","name":"FEDER","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002924","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\/iccv51701.2025.01688","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18166-18176","source":"Crossref","is-referenced-by-count":0,"title":["Anchor Token Matching: Implicit Structure Locking for Training-Free AR Image Editing"],"prefix":"10.1109","author":[{"given":"Taihang","family":"Hu","sequence":"first","affiliation":[{"name":"VCIP, College of Computer Science, Nankai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linxuan","family":"Li","sequence":"additional","affiliation":[{"name":"VCIP, College of Computer Science, Nankai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Vision Center, Universitat Autònoma de Barcelona"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaxing","family":"Wang","sequence":"additional","affiliation":[{"name":"NKIARI, Shenzhen Futian"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"VCIP, College of Computer Science, Nankai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"NKIARI, Shenzhen Futian"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_26"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00258"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref7","author":"Chen","year":"2023","journal-title":"Pixart- \\alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01166"},{"key":"ref9","article-title":"Janus-pro: Unified multi-modal understanding and generation with data and model scaling","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref11","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref12","article-title":"Guiding instruction-based image editing via multi-modal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_21"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02280"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01737"},{"key":"ref16","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Improving negative-prompt inversion via proximal guidance","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2023","journal-title":"ICLR"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"137646","article-title":"Token merging for trainingfree semantic binding in text-to-image synthesis","volume":"37","author":"Hu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1511-7"},{"key":"ref23","article-title":"Direct inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2023","journal-title":"ICLR"},{"key":"ref24","article-title":"Direct inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt1ffjfwg.15"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450462"},{"key":"ref27","article-title":"Controlar: Controllable image generation with autoregressive models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multi-modal generative pretraining","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3679-0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref32","article-title":"DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models","author":"Mou","year":"2024","journal-title":"ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00740"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0295-3"},{"key":"ref38","article-title":"Sdxl: improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"140","key":"ref40","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref41","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref42","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref46","volume-title":"Deepfloyd-if","author":"Shonenkov","year":"2023"},{"key":"ref47","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref49","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref52","article-title":"Conditional image generation with pixelcnn decoders","author":"Van den Oord","year":"2016","journal-title":"Advances in neural information processing systems, 29"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0887"},{"key":"ref54","article-title":"Dynamic prompt learning: Addressing cross-attention leakage for text-based image editing","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref55","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01210"},{"key":"ref58","article-title":"Show-o: One single transformer to unify multi-modal understanding and generation","author":"Xie","year":"2025","journal-title":"ICLR"},{"key":"ref59","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4184-4"}],"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\/11444474.pdf?arnumber=11444474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:11:49Z","timestamp":1777612309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01688","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}