{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:36:10Z","timestamp":1778081770542,"version":"3.51.4"},"reference-count":49,"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\/iccv51701.2025.01456","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15692-15702","source":"Crossref","is-referenced-by-count":2,"title":["LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models"],"prefix":"10.1109","author":[{"given":"Yu","family":"Cheng","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fajie","family":"Yuan","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"High-quality joint image and video tokenization with causal vae","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Argaw"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref4","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref5","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref6","volume-title":"Wavelets and wavelet transforms","volume":"98","author":"Burrus","year":"1998"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.29007\/h68j"},{"key":"ref8","article-title":"Od-vae: An omni-dimensional video compressor for improving latent video diffusion model","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2005.1530348"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref11","article-title":"Ltx-video: Realtime video latent diffusion","author":"HaCohen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Learnings from scaling visual tokenizers for reconstruction and generation","author":"Hansen-Estruch","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3366899"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_9"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv: Learning, arXiv: Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref19","volume-title":"Open-sora-plan","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3173256"},{"key":"ref21","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024","journal-title":"ArXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01656"},{"key":"ref23","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","volume-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024"},{"key":"ref25","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv:1704.00675"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref27","article-title":"Litevae: Lightweight and efficient variational autoencoders for latent diffusion models","author":"Sadat","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref30","article-title":"Vidtok: A versatile and open-source video tokenizer","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Fvd: A new metric for video generation","volume-title":"International Conference on Learning Representations, International Conference on Learning Representations","author":"Unterthiner","year":"2019"},{"key":"ref32","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"International Conference on Learning Representations","author":"Villegas","year":"2022"},{"key":"ref33","article-title":"Omnitokenizer: A joint image-video tokenizer for visual generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02134"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref36","volume-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Zhang","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01689"},{"key":"ref38","article-title":"Large motion video autoencoding with cross-modal video vae","author":"Xing","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00251"},{"key":"ref40","article-title":"Easyanimate: A high-performance long video generation method based on transformer architecture","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref44","volume-title":"Language model beats diffusion - tokenizer is key to visual generation","author":"Yu","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00196"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref47","article-title":"Cv-vae: A compatible video vae for latent generative video models","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","volume-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"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\/11444232.pdf?arnumber=11444232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:17Z","timestamp":1777613357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01456","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}