{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:31Z","timestamp":1777889671148,"version":"3.51.4"},"reference-count":45,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01593","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17150-17159","source":"Crossref","is-referenced-by-count":0,"title":["Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models"],"prefix":"10.1109","author":[{"given":"Xuran","family":"Ma","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yexin","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaofu","family":"Liu","sequence":"additional","affiliation":[{"name":"Everlyn AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianfeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhe","family":"Zheng","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihao","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ser-Nam","family":"Lim","sequence":"additional","affiliation":[{"name":"Everlyn AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harry","family":"Yang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/wics.101"},{"key":"ref2","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Temporal regularization makes your video generator stronger","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02636"},{"key":"ref5","article-title":"Delta-dit: A training-free acceleration method tailored for diffusion transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02190"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-76815-6_18"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1120"},{"key":"ref10","article-title":"Animate-a-story: Storytelling with retrieval-augmented video generation","author":"He","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","author":"Ho","year":"2020","journal-title":"Denoising diffusion probabilistic models"},{"key":"ref12","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref14","author":"Kahatapitiya","year":"2024","journal-title":"Adaptive caching for faster video generation with diffusion transformers"},{"key":"ref15","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","author":"Li","year":"2023","journal-title":"Snapfusion: Text-to-image diffusion model on mobile devices within two seconds"},{"key":"ref17","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","author":"Lin","year":"2025","journal-title":"Diffusion adversarial post-training for one-step video generation"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00689"},{"key":"ref20","article-title":"Faster diffusion via temporal attention decomposition","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CAI59869.2024.00175"},{"key":"ref22","author":"Lu","year":"2022","journal-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps"},{"key":"ref23","article-title":"Fastercache: Training-free video diffusion model acceleration with high quality","author":"Lv","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","author":"Ma","year":"2025","journal-title":"Step-video-t2v technical report: The practice, challenges, and future of video foundation model"},{"key":"ref25","article-title":"Dreamdance: Animating human images by enriching 3d geometry cues from 2d poses","author":"Pang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref27","author":"Polyak","year":"2025","journal-title":"Movie gen: A cast of media foundation models"},{"key":"ref28","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","author":"Selvaraju","year":"2024","journal-title":"Fora: Fast-forward caching in diffusion transformer acceleration"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00184"},{"key":"ref31","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref32","author":"Song","year":"2022","journal-title":"Denoising diffusion implicit models"},{"key":"ref33","year":"2025","journal-title":"Wan: Open and advanced large-scale video generative models"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3696409.3700181"},{"key":"ref35","article-title":"Lightgen: Efficient image generation through knowledge distillation and direct preference optimization","author":"Wu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730604"},{"key":"ref37","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Virbo: Multimodal multilingual avatar video generation in digital marketing","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3232543"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref41","article-title":"Moviedreamer: Hierarchical generation for coherent long visual sequence","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Real-time video generation with pyramid attention broadcast","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Videogen-of-thought: A collaborative framework for multi-shot video generation","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref45","author":"Zou","year":"2025","journal-title":"Accelerating diffusion transformers with tokenwise feature caching"}],"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\/11443525.pdf?arnumber=11443525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:17Z","timestamp":1777612457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443525\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01593","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}