{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:09:48Z","timestamp":1784268588828,"version":"3.55.0"},"reference-count":81,"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":["62032006"],"award-info":[{"award-number":["62032006"]}],"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\/iccv51701.2025.01718","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18487-18497","source":"Crossref","is-referenced-by-count":3,"title":["CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Hui","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dexiang","family":"Hong","sequence":"additional","affiliation":[{"name":"Bytedance Intelligent Creation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yitong","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance Intelligent Creation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Shao","sequence":"additional","affiliation":[{"name":"Bytedance Intelligent Creation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinglong","family":"Wu","sequence":"additional","affiliation":[{"name":"Bytedance Intelligent Creation,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv:2303.08774"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref3","article-title":"Improving image generation with better captions","author":"Betker","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_23"},{"key":"ref6","article-title":"Pixart-$\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen","year":"2024"},{"key":"ref7","article-title":"Reason out your layout: Evoking the layout master from large language models for text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv:2311.17126"},{"key":"ref8","article-title":"Visual programming for step-by-step text-to-image generation and evaluation","volume-title":"NeurIPS","author":"Cho","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_25"},{"key":"ref10","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv:2407.21783"},{"key":"ref11","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"arXiv preprint arXiv:2403.03206"},{"key":"ref12","article-title":"Layoutgpt: Compositional visual planning and generation with large language models","volume-title":"NeurIPS","author":"Feng","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"ref14","article-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv:2405.05945"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00633"},{"key":"ref16","article-title":"Gemma-7b-it","year":"2024"},{"key":"ref17","article-title":"Qwen-vl-chat-finetuned-dense-captioner","year":"2024"},{"key":"ref18","article-title":"Qwen2.5-7b-it","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_4"},{"key":"ref20","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"NeurIPS","author":"Heusel","year":"2017"},{"key":"ref21","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00591"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00015"},{"key":"ref24","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv:2106.09685"},{"key":"ref25","article-title":"Minicpm: Unveiling the potential of small language models with scalable training strategies","author":"Hu","year":"2024","journal-title":"arXiv preprint arXiv:2404.06395"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref27","article-title":"Qwen2.5-coder technical report","author":"Hui","year":"2024","journal-title":"arXiv preprint arXiv:2409.12186"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28024"},{"key":"ref29","article-title":"Yolov11: An overview of the key architectural enhancements","author":"Khanam","year":"2024","journal-title":"arXiv preprint arXiv:2410.17725"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref33","article-title":"Flux","year":"2024"},{"key":"ref34","article-title":"Laion-aesthetics v2","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1868"},{"key":"ref36","article-title":"Playground v2.5: Three insights towards enhancing aesthetic quality in text-to-image generation","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2402.17245"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01126"},{"key":"ref38","article-title":"Webvision database: Visual learning and understanding from web data","author":"Li","year":"2017","journal-title":"arXiv preprint arXiv:1708.02862"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref40","article-title":"Hunyuan-dit: A powerful multiresolution diffusion transformer with fine-grained chinese understanding","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2405.02324"},{"key":"ref41","article-title":"Llmgrounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2024","journal-title":"TMLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","article-title":"Playground v3: Improving text-toimage alignment with deep-fusion large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2409.10695"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref45","article-title":"Hico: Hierarchical controllable diffusion model for layout-to-image generation","volume-title":"NeurIPS","author":"Ma","year":"2025"},{"key":"ref46","article-title":"Llama-3.1-8b-instruct","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref48","article-title":"Compositional text-to-image generation with dense blob representations","author":"Nie","year":"2024","journal-title":"arXiv preprint arXiv:2405.08246"},{"key":"ref49","article-title":"Minicpm-v-2.6","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref52","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612012"},{"key":"ref54","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref55","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"JMLR"},{"key":"ref56","article-title":"Grounding dino 1.5: Advance the \u201cedge\u201d of open-set object detection","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv:2405.10300"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref58","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"NeurIPS","author":"Saharia","year":"2022"},{"key":"ref59","article-title":"Improved techniques for training gans","volume-title":"NeurIPS","author":"Salimans","year":"2016"},{"key":"ref60","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"NeurIPS","author":"Schuhmann","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00852"},{"key":"ref62","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song","year":"2021"},{"key":"ref63","article-title":"Stable diffusion 3.5","year":"2024"},{"key":"ref64","article-title":"Gemma: Open models based on gemini research and technology","author":"Mesnard","year":"2024","journal-title":"arXiv preprint arXiv:2403.08295"},{"key":"ref65","article-title":"Omost github page","year":"2024"},{"key":"ref66","article-title":"Unigen: Enhanced training & test-time strategies for unified multimodal understanding and generation","author":"Tian","year":"2025","journal-title":"arXiv preprint arXiv:2505.14682"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01209"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref70","article-title":"Ifadapter: Instance feature control for grounded text-to-image generation","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv:2409.08240"},{"key":"ref71","article-title":"Vidiff: Translating videos via multi-modal instructions with diffusion models","author":"Xing","year":"2023","journal-title":"arXiv preprint arXiv:2311.18837"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00748"},{"key":"ref73","article-title":"Aid: Adapting image2video diffusion models for instruction-guided video prediction","author":"Xing","year":"2024","journal-title":"arXiv preprint arXiv:2406.06465"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref75","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"NeurIPS","author":"Xu","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02072"},{"key":"ref78","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal llms","volume-title":"ICML","author":"Yang","year":"2024"},{"key":"ref79","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv:2308.06721"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"}],"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\/11444422.pdf?arnumber=11444422","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:24Z","timestamp":1777612104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444422\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01718","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}