{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:45Z","timestamp":1777865325369,"version":"3.51.4"},"reference-count":48,"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 R&D Program of China","doi-asserted-by":"publisher","award":["2024YFA1012700,2023YFF0725100"],"award-info":[{"award-number":["2024YFA1012700,2023YFF0725100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["62402410,U22B2060"],"award-info":[{"award-number":["62402410,U22B2060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2023A1515110131"],"award-info":[{"award-number":["2023A1515110131"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020084","name":"Guangzhou Municipal Science and Technology Bureau","doi-asserted-by":"publisher","award":["2024A04J4454"],"award-info":[{"award-number":["2024A04J4454"]}],"id":[{"id":"10.13039\/501100020084","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\/iccv51701.2025.00382","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4009-4018","source":"Crossref","is-referenced-by-count":0,"title":["Adding Additional Control to One-Step Diffusion with Joint Distribution Matching"],"prefix":"10.1109","author":[{"given":"Yihong","family":"Luo","sequence":"first","affiliation":[{"name":"HKUST"}]},{"given":"Tianyang","family":"Hu","sequence":"additional","affiliation":[{"name":"Huawei Noah&#x0027;s Ark Lab"}]},{"given":"Yifan","family":"Song","sequence":"additional","affiliation":[{"name":"HKUST(GZ)"}]},{"given":"Jiacheng","family":"Sun","sequence":"additional","affiliation":[{"name":"Huawei Noah&#x0027;s Ark Lab"}]},{"given":"Zhenguo","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah&#x0027;s Ark Lab"}]},{"given":"Jing","family":"Tang","sequence":"additional","affiliation":[{"name":"HKUST(GZ)"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00091"},{"key":"ref2","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref4","article-title":"Directly fine-tuning diffusion models on differentiable rewards","author":"Clark","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Emu: Enhancing image generation models using photogenic needles in a haystack","author":"Dai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref6","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","volume":"36","author":"Fan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref8","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":"ref9","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Aligning text-to-image models using human feedback","author":"Lee","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref11","article-title":"Instaflow: One step is enough for high-quality diffusion-based text-to-image generation","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref13","article-title":"Knowledge distillation in iterative generative models for improved sampling speed","author":"Luhman","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref14","article-title":"Latent consistency models: Synthesizing highresolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref15","volume-title":"Lcm-lora: A universal stable-diffusion acceleration module","author":"Luo","year":"2023"},{"key":"ref16","article-title":"Diff-instruct++: Training one-step text-toimage generator model to align with human preferences","author":"Luo","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3344"},{"key":"ref18","author":"Luo","year":"2024","journal-title":"You only sample once: Taming one-step text-toimage synthesis by self-cooperative diffusion gans"},{"key":"ref19","article-title":"The surprising effectiveness of skip-tuning in diffusion sampling","author":"Ma","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref22","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"Aligning text-to-image diffusion models with reward backpropagation","author":"Prabhudesai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref25","author":"Ren","year":"2024","journal-title":"Hyper-sd: Trajectory segmented consistency model for efficient image synthesis"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref27","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"International Conference on Learning Representations","author":"Salimans","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"ref31","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref32","article-title":"Improved techniques for training consistency models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Song","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/960128.806879"},{"key":"ref34","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Human preference score v 2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"CCM: Real-time controllable visual content creation using text-to-image consistency models","volume-title":"Forty-first International Conference on Machine Learning","author":"Xiao","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref38","article-title":"Imagere-ward: 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":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00792"},{"key":"ref40","article-title":"Perflow: Piecewise rectified flow as universal plug-and-play accelerator","author":"Yan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02180"},{"key":"ref42","article-title":"One-step diffusion with distribution matching distillation","author":"Yin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","author":"Yin","year":"2024","journal-title":"Improved distribution matching distillation for fast image synthesis"},{"key":"ref44","article-title":"Sdxs: Real-time onestep latent diffusion models with image conditions","author":"Yin","year":"2024","journal-title":"arxiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2170"},{"key":"ref47","volume-title":"Trajectory consistency distillation","author":"Zheng","year":"2024"},{"key":"ref48","article-title":"Score identity distillation: Exponentially fast distillation of pretrained diffusion models for one-step generation","volume-title":"International Conference on Machine Learning","author":"Zhou","year":"2024"}],"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\/11448987.pdf?arnumber=11448987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:42Z","timestamp":1777529802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11448987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00382","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}