{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:55:57Z","timestamp":1777888557169,"version":"3.51.4"},"reference-count":82,"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\/iccv51701.2025.01603","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"01-12","source":"Crossref","is-referenced-by-count":0,"title":["Trade-Offs in Image Generation: How Do Different Dimensions Interact?"],"prefix":"10.1109","author":[{"given":"Sicheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Khalifa University"}]},{"given":"Binzhu","family":"Xie","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Zhonghao","family":"Yan","sequence":"additional","affiliation":[{"name":"Queen Mary University of London"}]},{"given":"Yuli","family":"Zhang","sequence":"additional","affiliation":[{"name":"Queen Mary University of London"}]},{"given":"Donghao","family":"Zhou","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Xiaofei","family":"Chen","sequence":"additional","affiliation":[{"name":"Xi‘an Jiaotong-Liverpool University"}]},{"given":"Shi","family":"Qiu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Jiaqi","family":"Liu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong"}]},{"given":"Guoyang","family":"Xie","sequence":"additional","affiliation":[{"name":"City University of Hong Kong"}]},{"given":"Zhichao","family":"Lu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong"}]}],"member":"263","reference":[{"issue":"7","key":"ref1","first-page":"8","article-title":"Gpt-4 technical report","volume":"4","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"3","article-title":"Humanedit: A highquality human-rewarded dataset for instruction-based image editing","volume":"2","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01834"},{"key":"ref4","volume-title":"Improving image generation with better captions","author":"Betker","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594095"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01718"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"issue":"2","key":"ref9","first-page":"7","article-title":"Janus-pro: Unified multimodal understanding and generation with data and model scaling","volume":"1","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"2","article-title":"Mj-bench: Is your multimodal reward model really a good judge for text-to-image generation?","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"3","article-title":"Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image generation","author":"Cho","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0265"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","first-page":"594","article-title":"Tise: Bag of metrics for text-to-image synthesis evaluation","volume-title":"European Conference on Computer Vision","author":"Tan","year":"2022"},{"key":"ref16","first-page":"4","article-title":"How numerical precision affects mathematical reasoning capabilities of 11 ms","author":"Feng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"4","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.234"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref20","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00916"},{"key":"ref23","first-page":"2","article-title":"Dual-schedule inversion: Training-and tuning-free inversion for real image editing","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3531907"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"issue":"3","key":"ref26","first-page":"6","article-title":"Hq-edit: A high-quality dataset for instruction-based image editing","volume":"2","author":"Hui","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"2","article-title":"Direct inversion: Boosting diffusion-based editing with 3 lines of code","author":"Ju","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref32","article-title":"Black Forest Labs","volume-title":"Flux","year":"2024"},{"key":"ref33","first-page":"2","article-title":"One diffusion to generate them all","author":"Duong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3067"},{"issue":"3","key":"ref35","first-page":"1","article-title":"Genai-bench: Evaluating and improving compositional text-to-visual generation","volume":"2","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","first-page":"7","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01249"},{"key":"ref39","first-page":"2","article-title":"Schedule your edit: A simple yet effective diffusion noise schedule for image editing","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref41","article-title":"Revisiting the role of language priors in vision-language models","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_20"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref44","article-title":"Vladimir Mandic","volume-title":"Nudenet: Nsfw object detection for tfjs and nodejs","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_17"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref47","first-page":"2","article-title":"Human evaluation of text-to-image models on a multi-task benchmark","author":"Petsiuk","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","first-page":"2641","article-title":"Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"Bryan","year":"2015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/AIxVR63409.2025.00039"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/VRW66409.2025.00312"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref52","first-page":"3","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"ref55","first-page":"7","article-title":"Improving image captioning with better use of captions","volume":"2","author":"Shi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref56","first-page":"3","article-title":"Learn\u201d no\u201d to say\u201c yes\u201d better: Improving vision-language models via negations","author":"Singh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","first-page":"3","article-title":"Stability AI","volume-title":"Stable diffusion 3.5","volume":"7","year":"2024"},{"key":"ref58","first-page":"7","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","volume":"3","author":"Tan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","first-page":"7","article-title":"Qwen Team","volume-title":"Qwen2.5-vl","volume":"3","year":"2025"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00191"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"ref62","first-page":"3","author":"Wang","year":"2024","journal-title":"Lvbench: An extreme long video understanding benchmark"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref64","first-page":"2","article-title":"Omniedit: Building image editing generalist models through specialist supervision","volume":"4","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_12"},{"key":"ref66","first-page":"3","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"},{"issue":"4","key":"ref67","first-page":"6","article-title":"Omnigen: Unified image generation","volume":"2","author":"Xiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","first-page":"7","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","volume":"2","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"XLabs-AI","volume-title":"Flux ip adapter v2","year":"2024"},{"key":"ref70","first-page":"3","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0079"},{"key":"ref72","first-page":"3","article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","author":"Yuksekgonul","year":"2022","journal-title":"arXiv preprint"},{"key":"ref73","first-page":"73547363","article-title":"Self-attention generative adversarial networks","volume-title":"International conference on machine learning","author":"Zhang","year":"2019"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00766"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00862"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref78","first-page":"3","article-title":"Prompting visual-language models for dynamic facial expression recognition","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref79","first-page":"3","article-title":"VBench-2.0: Advancing video generation benchmark suite for intrinsic faithfulness","author":"Zheng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref80","first-page":"2","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","volume":"4","author":"Yang Qiaochu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1136"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1136"}],"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\/11444193.pdf?arnumber=11444193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:47:28Z","timestamp":1777610848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01603","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}