{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:29Z","timestamp":1777865369523,"version":"3.51.4"},"reference-count":44,"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":["62203257,62325405,62031017,62406159"],"award-info":[{"award-number":["62203257,62325405,62031017,62406159"]}],"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\/iccv51701.2025.01523","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16410-16419","source":"Crossref","is-referenced-by-count":0,"title":["Dlfr-Gen: Diffusion-Based Video Generation With Dynamic Latent Frame Rate"],"prefix":"10.1109","author":[{"given":"Zhihang","family":"Yuan","sequence":"first","affiliation":[{"name":"Tsinghua University Infinigence AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Xie","sequence":"additional","affiliation":[{"name":"Tsinghua University Infinigence AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhang","family":"Shang","sequence":"additional","affiliation":[{"name":"University of Central,Florida"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanling","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University Infinigence AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengen","family":"Yan","sequence":"additional","affiliation":[{"name":"Infinigence AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guohao","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"ref3","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022","journal-title":"arXiv preprint"},{"issue":"1","key":"ref4","volume":"3","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref5","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"arXiv preprint","author":"Chen","year":"2023"},{"key":"ref6","article-title":"Deep compression autoencoder for efficient high-resolution diffusion models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_36"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02060"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00418"},{"key":"ref14","article-title":"Adaptive caching for faster video generation with diffusion transformers","author":"Kahatapitiya","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref16","author":"Diederik","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref17","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","volume-title":"Flux","author":"Forest Labs","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref20","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351436"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref24","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref25","author":"Polyak","year":"2025","journal-title":"Movie gen: A cast of media foundation models"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref28","article-title":"Mediconfusion: Can you trust your ai radiologist? probing the reliability of multimodal medical foundation models","author":"Shahab Sepehri","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/76.915357"},{"key":"ref31","article-title":"Asymrnr: Video diffusion transformers acceleration with asymmetric reduction and restoration","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref33","author":"Vaswani","year":"2017","journal-title":"Attention is all you need. Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0887"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref36","article-title":"Godiva: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref38","article-title":"Sparse videogen: Accelerating video diffusion transformers with spatial-temporal sparsity","author":"Xi","year":"2025","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755638"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33071"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref42","article-title":"Crossattention makes inference cumbersome in text-to-image diffusion models","author":"Zhang","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref43","article-title":"Real-time video generation with pyramid attention broadcast","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024","journal-title":"arXiv preprint"}],"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\/11446211.pdf?arnumber=11446211","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:36Z","timestamp":1777530096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446211\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01523","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}