{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:05:24Z","timestamp":1780949124014,"version":"3.54.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["62321005"],"award-info":[{"award-number":["62321005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["624B1026"],"award-info":[{"award-number":["624B1026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62336004"],"award-info":[{"award-number":["62336004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125603"],"award-info":[{"award-number":["62125603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3665481","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:06:50Z","timestamp":1771276010000},"page":"7550-7563","source":"Crossref","is-referenced-by-count":0,"title":["FlowTurbo: Accelerating Flow-Based Image Generation Models via Multi-Stage Refinement"],"prefix":"10.1109","volume":"48","author":[{"given":"Wenliang","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6194-0915","authenticated-orcid":false,"given":"Minglei","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xumin","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5477-9764","authenticated-orcid":false,"given":"Zengyi","family":"Qin","sequence":"additional","affiliation":[{"name":"MIT Computer Science & Artificial Intelligence Laboratory, MIT Department of Aeronautics and Astronautics, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7701-234X","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref2","first-page":"240","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref6","article-title":"PIXART-{$\\backslash$\u2216delta}: Fast and controllable image generation with latent consistency models","volume-title":"Proc. ICML 2024 Workshop Theoretical Found. Found. Models","author":"Chen","year":"2024"},{"key":"ref7","article-title":"Hunyuan-DiT: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding","author":"Li","year":"2024"},{"key":"ref8","first-page":"60648","article-title":"SANA: Efficient high-resolution image synthesis with linear diffusion transformers","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Xie","year":"2025"},{"key":"ref9","first-page":"10328","article-title":"Novel view synthesis with diffusion models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Watson","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01204"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref14","first-page":"31194","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Poole","year":"2023"},{"key":"ref15","first-page":"5775","article-title":"DPM-Solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2022"},{"key":"ref16","first-page":"5954","article-title":"Pseudo numerical methods for diffusion models on manifolds","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2170"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_26"},{"key":"ref19","first-page":"4998","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Salimans","year":"2022"},{"key":"ref20","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. 40th Int. Conf. Mach. Learn., ser. Proc. Mach. Learn. Res.","volume":"202","author":"Song","year":"2023"},{"key":"ref21","first-page":"15078","article-title":"Improved techniques for training consistency models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2024"},{"key":"ref22","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023"},{"key":"ref23","first-page":"50611","article-title":"Simplifying, stabilizing and scaling continuous-time consistency models","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"Lu","year":"2025"},{"key":"ref24","first-page":"42947","article-title":"Align your steps: Optimizing sampling schedules in diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sabour","year":"2024"},{"key":"ref25","first-page":"6571","article-title":"Neural ordinary differential equations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2018"},{"key":"ref26","first-page":"23666","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref27","first-page":"22698","article-title":"Flow matching for generative modeling","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Lipman","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02126"},{"key":"ref29","article-title":"Motion flow matching for human motion synthesis and editing","author":"Hu","year":"2023"},{"key":"ref30","first-page":"338","article-title":"Boosting latent diffusion with flow matching","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Fischer","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29056"},{"key":"ref32","article-title":"Enabling visual composition and animation in unsupervised video generation","author":"Davtyan","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32330"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-short.33"},{"key":"ref35","first-page":"20060","article-title":"InstaFlow: One step is enough for high-quality diffusion-based text-to-image generation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref37","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref38","first-page":"21604","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1505"},{"key":"ref41","first-page":"87","article-title":"Adversarial diffusion distillation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Sauer","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687625"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref44","article-title":"FLUX: A powerful tool for text generation","author":"Labs","year":"2024"},{"key":"ref45","article-title":"Open-Sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref46","article-title":"Lumina-T2X: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref50","article-title":"ControlNeXt: Powerful and efficient control for image and video generation","author":"Peng","year":"2024"},{"key":"ref51","article-title":"IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref52","article-title":"InstantID: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00010"},{"key":"ref54","first-page":"14205","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1505"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref57","first-page":"1","article-title":"CLEAR: Conv-like linearization revs pre-trained diffusion transformers up","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2025"},{"key":"ref58","first-page":"15417","article-title":"Bespoke solvers for generative flow models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Shaul","year":"2024"},{"key":"ref59","first-page":"18957","article-title":"Minimizing trajectory curvature of ODE-based generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2023"},{"key":"ref60","first-page":"28100","article-title":"Multisample flow matching: Straightening flows with minibatch couplings","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pooladian","year":"2023"},{"key":"ref61","first-page":"1","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","author":"Tong","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref62","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"issue":"209","key":"ref63","first-page":"1","article-title":"Stochastic interpolants: A unifying framework for flows and diffusions","volume":"26","author":"Albergo","year":"2025","journal-title":"J. Mach. Learn. Res."},{"key":"ref64","volume-title":"Numerical Methods for Ordinary Differential Systems","author":"Lambert","year":"1991"},{"key":"ref65","first-page":"13781","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Meng","year":"2021"},{"key":"ref66","article-title":"Stable diffusion 3.5 large","author":"AI","year":"2024"},{"key":"ref67","article-title":"Comfyui","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530738"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref70","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dhariwal","year":"2021"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref75","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref76","first-page":"57611","article-title":"PixArt-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2024","author":"Chen","year":"2024"},{"key":"ref77","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11397502.pdf?arnumber=11397502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:51:42Z","timestamp":1780948302000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397502\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":77,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3665481","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}