{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:07:30Z","timestamp":1784210850368,"version":"3.55.0"},"reference-count":94,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2095,12326618,62276281"],"award-info":[{"award-number":["U22A2095,12326618,62276281"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01562","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16818-16829","source":"Crossref","is-referenced-by-count":1,"title":["Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis"],"prefix":"10.1109","author":[{"given":"Yanzuo","family":"Lu","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxi","family":"Ren","sequence":"additional","affiliation":[{"name":"ByteDance Seed Vision"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Xia","sequence":"additional","affiliation":[{"name":"ByteDance Seed Vision"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanchuan","family":"Lin","sequence":"additional","affiliation":[{"name":"ByteDance Seed Vision"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Seed Vision"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefeng","family":"Xiao","sequence":"additional","affiliation":[{"name":"ByteDance Seed Vision"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andy J.","family":"Ma","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohua","family":"Xie","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian-Huang","family":"Lai","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Black Forest Labs","volume-title":"Flux.1-dev","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.08500"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33722"},{"key":"ref4","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref6","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref7","article-title":"Consistency models made easy","author":"Geng","year":"2025","journal-title":"ICLR"},{"key":"ref8","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref11","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS Workshops","author":"Ho","year":"2021"},{"key":"ref12","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ipdpsw63119.2024.00208"},{"key":"ref16","article-title":"Score-of-mixture training: Training one-step generative models made simple via score estimation of mixture distributions","author":"Jayashankar","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref17","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Consistency trajectory models: Learning probability flow ode trajectory of diffusion","author":"Kim","year":"2024","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref21","article-title":"Imagine flash: Accelerating emu diffusion models with backward distillation","author":"Kohler","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Geometric gan","author":"Lim","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"Sdxllightning: Progressive adversarial diffusion distillation","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref24","article-title":"Diffusion adversarial post-training for one-step video generation","author":"Lin","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref26","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"I C L R"},{"key":"ref28","article-title":"Instaflow: One step is enough for high-quality diffusion-based text-to-image generation","author":"Liu","year":"2024","journal-title":"ICLR"},{"key":"ref29","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref30","article-title":"Simplifying, stabilizing and scaling continuous-time consistency models","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref31","first-page":"509","article-title":"Improving pre-trained masked autoencoder via locality enhancement for person reidentification","author":"Lu","year":"2022","journal-title":"PRCV"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28182"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00614"},{"key":"ref34","article-title":"Latent consistency models: Synthesizing highresolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Lcm-lora: A universal stable-diffusion acceleration module","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Diff-instruct++: Training one-step text-toimage generator model to align with human preferences","author":"Luo","year":"2024","journal-title":"TMLR"},{"key":"ref37","first-page":"76525","article-title":"Diff-instruct: A universal approach for transferring knowledge from pre-trained diffusion models","author":"Luo","year":"2023","journal-title":"NeurIPS"},{"key":"ref38","article-title":"One-step diffusion distillation through score implicit matching","author":"Luo","year":"2024","journal-title":"NeurIPS"},{"key":"ref39","article-title":"David and goliath: Small one-step model beats large diffusion with score post-training","author":"Luo","year":"2025","journal-title":"ICML"},{"key":"ref40","article-title":"You only sample once: Taming one-step text-toimage synthesis by self-cooperative diffusion gans","author":"Luo","year":"2025","journal-title":"ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755484"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755483"},{"key":"ref43","article-title":"Osv: One step is enough for high-quality image to video generation","author":"Mao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01975"},{"key":"ref45","article-title":"Divergence measures and message passing","author":"Minka","year":"2005","journal-title":"Microsoft Research, Technical Report"},{"key":"ref46","article-title":"Movie Gen Team","volume-title":"Movie gen: A cast of media foundation models","year":"2024"},{"key":"ref47","article-title":"Openvid-1m: A large-scale high-quality dataset for text-tovideo generation","author":"Nan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"TMLR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref50","volume-title":"Open-sora-planv1.1.0","author":"Lab","year":"2024"},{"key":"ref51","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2023","journal-title":"ICLR"},{"key":"ref52","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref54","article-title":"Searching for activation functions","author":"Ramachandran","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref55","article-title":"Hyper-sd: Trajectory segmented consistency model for efficient image synthesis","author":"Ren","year":"2024","journal-title":"NeurIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref58","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"ICLR"},{"key":"ref59","article-title":"Multistep distillation of diffusion models via moment matching","author":"Salimans","year":"2024","journal-title":"NeurIPS"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687625"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612211"},{"key":"ref63","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref64","article-title":"Improved techniques for training consistency models","author":"Song","year":"2024","journal-title":"ICLR"},{"key":"ref65","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref66","article-title":"Consistency models","author":"Song","year":"2023","journal-title":"ICML"},{"key":"ref67","article-title":"Journeydb: A benchmark for generative image understanding","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1002\/sta4.224"},{"key":"ref69","article-title":"Phased consistency model","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3681758.3698013"},{"key":"ref71","article-title":"Rectified diffusion: Straightness is not your need in rectified flow","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref72","author":"Wang","year":"2019","journal-title":"Bfloat16: The secret to high performance on cloud tpus"},{"key":"ref73","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref74","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref75","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":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.06.032"},{"key":"ref78","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","author":"Xu","year":"2023","journal-title":"NeurIPS"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01483"},{"key":"ref81","article-title":"Perflow: Piecewise rectified flow as universal plug-and-play accelerator","author":"Yan","year":"2024","journal-title":"NeurIPS"},{"key":"ref82","article-title":"Vript: A video is worth thousands of words","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref83","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref84","article-title":"Magic 1-for-1: Generating one minute video clips within one minute","author":"Yi","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref85","article-title":"Improved distribution matching distillation for fast image synthesis","author":"Yin","year":"2024","journal-title":"NeurIPS"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref87","article-title":"From slow bidirectional to fast causal video generators","author":"Yin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref88","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"TMLR"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00766"},{"key":"ref91","article-title":"Sf-v: Single forward video generation model","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"key":"ref92","article-title":"Trajectory consistency distillation: Improved latent consistency distillation by semi-linear consistency function with trajectory mapping","author":"Zheng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref93","article-title":"Score identity distillation: Exponentially fast distillation of pretrained diffusion models for one-step generation","author":"Zhou","year":"2024","journal-title":"ICML"},{"key":"ref94","article-title":"Adversarial score identity distillation: Rapidly surpassing the teacher in one step","author":"Zhou","year":"2025","journal-title":"ICLR"}],"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\/11445471.pdf?arnumber=11445471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:18:04Z","timestamp":1777612684000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":94,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01562","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}