{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:28Z","timestamp":1777889128589,"version":"3.51.4"},"reference-count":55,"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 Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62425114,62121002,U23B2028,62232006"],"award-info":[{"award-number":["62425114,62121002,U23B2028,62232006"]}],"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\/iccv51701.2025.01693","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18218-18228","source":"Crossref","is-referenced-by-count":0,"title":["Igd: Instructional Graphic Design With Multimodal Layer Generatio"],"prefix":"10.1109","author":[{"given":"Yadong","family":"Qu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}]},{"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"YuanShi Technology"}]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"YuanShi Technology"}]},{"given":"Shancheng","family":"Fang","sequence":"additional","affiliation":[{"name":"YuanShi Technology"}]},{"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}]},{"given":"Xiaorui","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}]},{"given":"Zhineng","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6","journal-title":"Canvagpt - effortlessly design anything: presentations, logos, social media posts and more"},{"key":"ref2","first-page":"2","year":"2023","journal-title":"Gpt-4v(ision) system card"},{"key":"ref3","first-page":"1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01343"},{"key":"ref6","first-page":"1","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","first-page":"2","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"3","article-title":"ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv preprint"},{"issue":"3","key":"ref9","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0410"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32249"},{"key":"ref12","first-page":"1","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt qualit"},{"key":"ref13","first-page":"2","article-title":"Dreamllm: Synergistic multimodal comprehension and creation","author":"Dong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/124"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3525526"},{"key":"ref16","first-page":"6","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"In Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref17","first-page":"2","article-title":"Layoutgpt: Compositional visual planning and generation with large language models","volume":"36","author":"Feng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"2","article-title":"Making llama see and draw with seed tokenizer","author":"Ge","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"2","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"8131","article-title":"Opencole: Towards reproducible automatic graphic design generation","volume-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Inoue","year":"2024"},{"key":"ref22","first-page":"3","article-title":"Cole: A hierarchical generation framework for multi-layered and editable graphic design","author":"Jia","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"2","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language model"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611930"},{"key":"ref25","first-page":"3","article-title":"Character-aware models improve visual text rendering","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_21"},{"key":"ref27","first-page":"3","article-title":"Glyphdraw: Learning to draw chinese characters in image synthesis models coherently","volume":"2","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"5","author":"NovelAI","year":"2023","journal-title":"Novelai improvements on stable diffusio"},{"key":"ref29","first-page":"5","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3348"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford","year":"2021"},{"issue":"140","key":"ref32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref35","first-page":"4","author":"Selinger","year":"2003","journal-title":"Potrace: a polygon-based tracing algorith"},{"key":"ref36","first-page":"3","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"2","article-title":"Emu: Generative pretraining in multimodality","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Sun","year":"2023"},{"key":"ref38","first-page":"2","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Chameleon Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.09396"},{"key":"ref40","article-title":"Anytext: Multilingual visual text generation and editing","author":"Tuo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","first-page":"2","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref42","first-page":"4","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","first-page":"2","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01210"},{"key":"ref45","first-page":"2","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","first-page":"4","article-title":"Qwen2.5 technical report","author":"Yang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref47","first-page":"2","article-title":"Posterllava: Constructing a unified multi-modal layout generator with 11 m","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","first-page":"2","article-title":"Glyphcontrol: Glyph conditional control for visual text generation","volume":"36","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","first-page":"2","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","first-page":"3","article-title":"How control information influences multilingual text image generation and editing","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01880-0"},{"key":"ref53","first-page":"2","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/692"},{"key":"ref55","first-page":"2","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"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\/11445066.pdf?arnumber=11445066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:49Z","timestamp":1777612069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445066\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01693","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}