{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:17:38Z","timestamp":1783455458265,"version":"3.55.0"},"reference-count":102,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["92467104"],"award-info":[{"award-number":["92467104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Leading Innovative and Entrepreneur Team Introduction Program","award":["2024R01007"],"award-info":[{"award-number":["2024R01007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3676894","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:07:33Z","timestamp":1774296453000},"page":"9156-9167","source":"Crossref","is-referenced-by-count":0,"title":["One-Step Diffusion and Flow Distillation Through Implicit Generator Matching"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2796-3133","authenticated-orcid":false,"given":"Zemin","family":"Huang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9647-3991","authenticated-orcid":false,"given":"Weijian","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyang","family":"Geng","sequence":"additional","affiliation":[{"name":"Computer Science Department, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3508-1851","authenticated-orcid":false,"given":"Guojun","family":"Qi","sequence":"additional","affiliation":[{"name":"MAPLE Lab, School of Engineering, Westlake University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref2","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref3","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref4","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2022"},{"key":"ref5","article-title":"Flow matching for generative modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lipman","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref8","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref9","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. SSW","author":"Oord","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref11","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Poole","year":"2022"},{"key":"ref12","first-page":"8867","article-title":"Equivariant diffusion for molecule generation in 3D","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hoogeboom","year":"2022"},{"key":"ref13","first-page":"11119","article-title":"Guided-TTS: A diffusion model for text-to-speech via classifier guidance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2022"},{"key":"ref14","first-page":"10215","article-title":"Glow: Generative flow with invertible 1 \u00d7 1 convolutions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma","year":"2018"},{"key":"ref15","first-page":"9916","article-title":"Residual flows for invertible generative modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2019"},{"key":"ref16","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Podell","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref18","article-title":"eDiff-I: Text-to-image diffusion models with ensemble of expert denoisers","author":"Balaji","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1806"},{"key":"ref20","article-title":"Pixart-$\\alpha$\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref24","article-title":"SDEdit: Image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref25","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Couairon","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2257"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3392"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref34","article-title":"Prompt-to-prompt image editing with cross attention control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hertz","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref36","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal","year":"2022"},{"key":"ref37","first-page":"72137","article-title":"Patch diffusion: Faster and more data-efficient training of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref38","article-title":"Truncated diffusion probabilistic models and diffusion-based adversarial auto-encoders","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zheng","year":"2022"},{"key":"ref39","article-title":"Diffusion-GAN: Training GANs with diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2022"},{"key":"ref40","article-title":"Data prediction denoising models: The pupil outdoes the master","author":"Luo","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3392"},{"key":"ref42","article-title":"Training energy-based models with diffusion contrastive divergences","author":"Luo","year":"2023"},{"key":"ref43","article-title":"Purify++: Improving diffusion-purification with advanced diffusion models and control of randomness","author":"Zhang","year":"2023"},{"key":"ref44","article-title":"A Lipschitz bandits approach for continuous hyperparameter optimization","author":"Feng","year":"2023"},{"key":"ref45","first-page":"10506","article-title":"Variational Schr\u00f6dinger diffusion models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Deng","year":"2024"},{"key":"ref46","first-page":"7137","article-title":"Entropy-based training methods for scalable neural implicit samplers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo","year":"2024"},{"key":"ref47","article-title":"Consistency models made easy","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Geng","year":"2024"},{"key":"ref48","article-title":"Integrating amortized inference with diffusion models for learning clean distribution from corrupted images","author":"Wang","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2752"},{"key":"ref50","first-page":"10506","article-title":"Variational Schr\u00f6dinger diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Deng","year":"2024"},{"key":"ref51","first-page":"1","article-title":"Stochastic interpolants: A unifying framework for flows and diffusions","author":"Albergo","year":"2023","journal-title":"J. Mach. Learn. Research"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3344"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00632"},{"key":"ref54","first-page":"62307","article-title":"Score identity distillation: Exponentially fast distillation of pretrained diffusion models for one-step generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou","year":"2024"},{"key":"ref55","article-title":"Consistency flow matching: Defining straight flows with velocity consistency","author":"Yang","year":"2024"},{"key":"ref56","article-title":"Simplifying, stabilizing and scaling continuous-time consistency models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3725"},{"key":"ref59","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref62","article-title":"Building normalizing flows with stochastic interpolants","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Albergo","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3664"},{"key":"ref64","article-title":"A comprehensive survey on knowledge distillation of diffusion models","author":"Luo","year":"2023"},{"key":"ref65","article-title":"Knowledge distillation in iterative generative models for improved sampling speed","author":"Luhman","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1816"},{"key":"ref67","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Salimans","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref69","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song","year":"2023"},{"key":"ref70","article-title":"Consistency trajectory models: Learning probability flow ode trajectory of diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2023"},{"key":"ref71","article-title":"Improved techniques for training consistency models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32580"},{"key":"ref73","article-title":"BOOT: Data-free distillation of denoising diffusion models with bootstrapping","author":"Gu","year":"2023"},{"key":"ref74","article-title":"Tackling the generative learning trilemma with denoising diffusion GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiao","year":"2021"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"ref76","article-title":"Autoregressive adversarial post-training for real-time interactive video generation","volume-title":"Proc. Int. Conf. Neural Inf. Process","author":"Lin","year":"2025"},{"key":"ref77","first-page":"37959","article-title":"Diffusion adversarial post-training for one-step video generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin","year":"2025"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3344"},{"key":"ref79","article-title":"Uni-Instruct: One-step diffusion model through unified diffusion divergence instruction","volume-title":"Proc. Int. Conf. Neural Inf. Process","author":"Wang","year":"2025"},{"key":"ref80","article-title":"Fast sampling of diffusion models with exponential integrator","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2022"},{"key":"ref81","article-title":"Flow map matching","author":"Boffi","year":"2024"},{"key":"ref82","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00746"},{"key":"ref84","article-title":"SDXS: Real-time one-step latent diffusion models with image conditions","author":"Song","year":"2024"},{"key":"ref85","article-title":"Long and short guidance in score identity distillation for one-step text-to-image generation","author":"Zhou","year":"2024"},{"key":"ref86","article-title":"The CIFAR-10 dataset","author":"Krizhevsky","year":"2014"},{"key":"ref87","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock","year":"2019"},{"key":"ref88","first-page":"12104","article-title":"Training generative adversarial networks with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karras","year":"2020"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530738"},{"key":"ref90","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33722"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref93","article-title":"Trajectory consistency distillation","author":"Zheng","year":"2024"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2497"},{"key":"ref95","article-title":"SDXL-lightning: Progressive adversarial diffusion distillation","author":"Lin","year":"2024"},{"key":"ref96","first-page":"4195","article-title":"Scalable diffusion models with transformers","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Peebles","year":"2022"},{"key":"ref97","article-title":"Improved-aesthetic-predictor","year":"2022"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref101","article-title":"Mini-DALLE3: Interactive text to image by prompting large language models","author":"Zeqiang","year":"2023"},{"key":"ref102","article-title":"Improving image generation with better captions","author":"Betker","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11454572.pdf?arnumber=11454572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:43Z","timestamp":1783453483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11454572\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":102,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3676894","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":[[2026,8]]}}}