{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:20:22Z","timestamp":1777890022227,"version":"3.51.4"},"reference-count":49,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01796","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19321-19330","source":"Crossref","is-referenced-by-count":0,"title":["SEGA: A Stepwise Evolution Paradigm for Content-Aware Layout Generation with Design Prior"],"prefix":"10.1109","author":[{"given":"Haoran","family":"Wang","sequence":"first","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghui","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanzhang","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Yang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Ji","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyan","family":"Xiao","sequence":"additional","affiliation":[{"name":"Baidu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","author":"Bai","year":"2023","journal-title":"Qwen-vl: A frontier large vision-language model with versatile abilities"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01227"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366160"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548332"},{"key":"ref6","author":"Chen","year":"2023","journal-title":"Reason out your layout: Evoking the layout master from large language models for text-to-image synthesis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32249"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445117"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00583"},{"key":"ref12","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00980"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01373"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_6"},{"key":"ref16","author":"Jia","year":"2023","journal-title":"Cole: A hierarchical generation framework for graphic design"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01765"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00999"},{"key":"ref19","article-title":"Thinking, fast and slow","volume-title":"Farrar, Straus and Giroux","author":"Kahneman","year":"2011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_29"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_29"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615028"},{"key":"ref23","author":"Li","year":"2019","journal-title":"Layoutgan: Generating graphic layouts with wireframe discriminators"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.2999335"},{"key":"ref25","article-title":"Layoutprompter: Awaken the design ability of large language models","volume-title":"NeurIPS","volume":"36","author":"Lin","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref28","author":"Menon","year":"2022","journal-title":"Visual classification via description from large language models"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1159\/000113158"},{"key":"ref30","author":"Mirzadeh","year":"2024","journal-title":"Gsmsymbolic: Understanding the limitations of mathematical reasoning in large language models"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2014.48"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3030448"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_26"},{"key":"ref34","author":"Sutskever","year":"2014","journal-title":"Sequence to sequence learning with neural networks"},{"key":"ref35","author":"Tang","year":"2023","journal-title":"Layoutnuwa: Revealing the hidden layout expertise of large language models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.36834\/cmej.36777"},{"key":"ref37","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref39","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref42","author":"Wu","year":"2023","journal-title":"Bloomberggpt: A large language model for finance"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00543"},{"key":"ref44","author":"Yang","year":"2023","journal-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0917-8_4"},{"key":"ref46","author":"Young","year":"2024","journal-title":"Yi: Open foundation models by 01. ai"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00664"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322971"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/692"}],"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\/11444711.pdf?arnumber=11444711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:24:45Z","timestamp":1777613085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01796","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}