{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:53:08Z","timestamp":1779346388603,"version":"3.51.4"},"reference-count":54,"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\/iccv51701.2025.01666","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17930-17940","source":"Crossref","is-referenced-by-count":1,"title":["Hybrid Layout Control for Diffusion Transformer: Fewer Annotations, Superior Aesthetics"],"prefix":"10.1109","author":[{"given":"Keming","family":"Wu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junwen","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanhao","family":"Liang","sequence":"additional","affiliation":[{"name":"The Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinuo","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhui","family":"Yuan","sequence":"additional","affiliation":[{"name":"Canva"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Aesthetic score v2.5"},{"key":"ref2","article-title":"Phi-4 technical report","author":"Abdin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"MultiDiffusion: Fusing diffusion paths for controlled image generation","volume-title":"ICML","author":"Bar-Tal","year":"2023"},{"key":"ref4","article-title":"Improving image generation with better captions","volume-title":"Computer Science","author":"Betker","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref7","article-title":"Training-free regional prompting for diffusion transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen","year":"2024"},{"key":"ref9","article-title":"Prismlayers: Open data for high-quality multi layer transparent image generative models","author":"Chen","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref11","article-title":"Emu: Enhancingim agegenerationmodelsusingphotogenicneedlesinahaystack","author":"Dai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0047-259X(82)90077-X"},{"key":"ref13","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":"ref14","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","article-title":"Training-free structured diffusion guidance for compositional text-to-image synthesis","author":"Feng","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref17","article-title":"LayoutGPT: Compositionalvisualplanning and generation with large language models","volume-title":"NeurIPS","author":"Feng","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref20","article-title":"COLE: A hierarchical generation frame work for graphic design","author":"Jia","year":"2023","journal-title":"arXiv:2311.16974"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref22","volume-title":"Flux.1 model family","year":"2024"},{"key":"ref23","volume-title":"Flux","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01356"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4094"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32643"},{"key":"ref28","article-title":"Prodigy: An expeditiously adaptive parameter-free learner","author":"Mishchenko","year":"2023","journal-title":"arXiv:2306.06101"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02546"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00153"},{"key":"ref31","article-title":"Compositional text-to-image generation with dense blob representations","author":"Nie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Bizgen: Advancingarticle-levelvisualtextrenderingforinfo graphics generation","author":"Peng","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref34","article-title":"Sdxl: Improving latent diffusion models for high resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00745"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00416"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref39","volume-title":"Omost github page","year":"2024"},{"key":"ref40","article-title":"FIX-CLIP: Dual-BranchHierarchicalContrastiveLearningviaSynthetic Captions for Better Understanding of Long Text","author":"Wang","year":"2025","journal-title":"arXiv e prints"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref42","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02072"},{"key":"ref46","article-title":"Mastering text-to-image diffusion: Re captioning, planning, and generating with multimodal LLMs","volume-title":"ICML","author":"Yang","year":"2024"},{"key":"ref47","article-title":"Creatilayout: Siamese multimodal diffusion transformer for creative layout-to-image generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"IterComp: Iterative composition-aware feedback learning from model gallery for text-to-image generation","author":"Zhang","year":"2024","journal-title":"arXiv:2410.07171"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01411"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3510752"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref53","article-title":"3dis: Depth-driven decoupled instance synthesis for text-to-image generation","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","article-title":"3dis f lux: simple and efficient multi-instance generation with dit rendering","author":"Zhou","year":"2025","journal-title":"arXiv preprint arXiv"}],"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\/11444020.pdf?arnumber=11444020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:45:55Z","timestamp":1777531555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01666","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}