{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:30Z","timestamp":1777890150283,"version":"3.51.4"},"reference-count":46,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFE0203700"],"award-info":[{"award-number":["2024YFE0203700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376243,62441617"],"award-info":[{"award-number":["62376243,62441617"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004502","name":"\u201cPioneer\u201d","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004502","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022963","name":"Key R&D Program of Zhejiang","doi-asserted-by":"publisher","award":["2025C01128"],"award-info":[{"award-number":["2025C01128"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2025-00057"],"award-info":[{"award-number":["226-2025-00057"]}],"id":[{"id":"10.13039\/501100012226","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\/iccv51701.2025.01690","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Decoding Correlation-Induced Misalignment in the Stable Diffusion Workflow for Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Yunze","family":"Tong","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengda","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Didi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Kuang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,Zhejiang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_1"},{"key":"ref3","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_25"},{"key":"ref7","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref8","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref9","volume-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref10","article-title":"Causal agent based on large language model","author":"Han","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref11","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","volume-title":"International Conference on Learning Representations","author":"He","year":"2021"},{"key":"ref12","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref13","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":"ref14","volume-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00686"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02198"},{"key":"ref18","article-title":"D-fusion: Direct preference optimization for aligning diffusion models with visually consistent samples","author":"Hu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110640"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1679"},{"key":"ref21","volume-title":"Black Forest Labs. Flux.","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref23","article-title":"Multimodal 11 m -guided semantic correction in text-to-image diffusion","author":"Lv","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709335"},{"key":"ref25","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref28","article-title":"Liu","author":"Raffel","year":"2023","journal-title":"Exploring the limits of transfer learning with a unified text-to-text transformer"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref31","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole","volume-title":"Score-based generative modeling through stochastic differential equations.","author":"Song","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599481"},{"key":"ref34","article-title":"Latent score-based reweighting for robust classification on imbal-anced tabular data","volume-title":"Forty-second International Conference on Machine Learning","author":"Tong","year":"2025"},{"key":"ref35","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref38","article-title":"Causality for large language models","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref40","article-title":"Unveiling and harnessing hidden attention sinks: Enhancing large language models without training through attention calibration","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Mixed-type tabular data synthesis with score-based diffusion in latent space","volume-title":"The twelfth International Conference on Learning Representations","author":"Zhang","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref43","article-title":"Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00456"},{"key":"ref45","article-title":"Moviedreamer: Hierarchical generation for coherent long visual sequence","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","article-title":"Diception: A generalist diffusion model for visual perceptual tasks","author":"Zhao","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\/11445022.pdf?arnumber=11445022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:21Z","timestamp":1777613481000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445022\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01690","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}