{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:54Z","timestamp":1777888674502,"version":"3.51.4"},"reference-count":78,"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":["62032006,62472098"],"award-info":[{"award-number":["62032006,62472098"]}],"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\/iccv51701.2025.01788","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19237-19247","source":"Crossref","is-referenced-by-count":1,"title":["REDUCIO! Generating 1K Video Within 16 Seconds Using Extremely Compressed Motion Latents"],"prefix":"10.1109","author":[{"given":"Rui","family":"Tian","sequence":"first","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Dai","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianmin","family":"Bao","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Qiu","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Luo","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","author":"An","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02190"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"ICML"},{"key":"ref10","article-title":"Dimba: Transformer-mamba diffusion models","author":"Fei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00684"},{"key":"ref14","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2023","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02386-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref18","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref19","volume-title":"Kling.","author":"Kling","year":"2024"},{"key":"ref20","volume-title":"Flux.1.","year":"2014"},{"key":"ref21","article-title":"Stiv: Scalable text and image conditioned video generation","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref23","article-title":"Instaflow: One step is enough for high-quality diffusion-based text-to-image generation","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref25","article-title":"Knowledge distillation in iterative generative models for improved sampling speed","author":"Luhman","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Token-shuffle: Towards high-resolution image generation with autoregressive models","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Deepstack: Deeply stacking visual tokens is surprisingly simple and effective for lmms","author":"Meng","year":"2024","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2022","journal-title":"ICML"},{"key":"ref29","article-title":"Improved denoising diffusion probabilistic models","author":"Nichol","year":"2021","journal-title":"ICML"},{"key":"ref30","article-title":"A suite of image and video neural tokenizers","volume-title":"A suite of image and video neural tokenizers.","author":"Cosmos Tokenizer","year":"2024"},{"key":"ref31","volume-title":"Sora.","author":"Sora","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref33","article-title":"W\u00fcrstchen: An efficient architecture for large-scale text-to-image diffusion models","author":"Pernias","year":"2024","journal-title":"ICLR"},{"key":"ref34","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2024","journal-title":"ICLR"},{"key":"ref35","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00634"},{"key":"ref37","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"JMLR"},{"key":"ref38","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"Rezende","year":"2014","journal-title":"ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/9780470989418"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","volume-title":"Gen-3.","year":"2024"},{"key":"ref42","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2023","journal-title":"ICLR"},{"key":"ref43","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref44","article-title":"Consistency models","author":"Song","year":"2023","journal-title":"ICML"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref46","article-title":"Hart: Efficient visual generation with hybrid autoregressive transformer","author":"Tang","year":"2025","journal-title":"ICLR"},{"key":"ref47","article-title":"Dim: Diffusion mamba for efficient high-resolution image synthesis","author":"Teng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01825"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00753"},{"key":"ref50","article-title":"Motionfollower: Editing video motion via lightweight score-guided diffusion","author":"Tu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01965"},{"key":"ref52","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Omnitokenizer: A joint image-video tokenizer for visual generation","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref54","article-title":"Simplear: Pushing the frontier of autoregressive visual generation through pre-training, sft, and rl","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02349-y"},{"key":"ref56","article-title":"Videocomposer: Compositional video synthesis with motion controllability","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00804"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref60","article-title":"Patch diffusion: Faster and more data-efficient training of diffusion models","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00735"},{"key":"ref62","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","author":"Xie","year":"2025","journal-title":"ICLR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00748"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3696415"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"ref68","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2025","journal-title":"ICLR"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02138"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"ref71","article-title":"Efficient video diffusion models via content-frame motion-latent decomposition","author":"Yu","year":"2024","journal-title":"ICLR"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33075"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref76","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"Real-time video generation with pyramid attention broadcast","author":"Zhao","year":"2025","journal-title":"ICLR"},{"key":"ref78","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\/11444683.pdf?arnumber=11444683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:50Z","timestamp":1777611230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01788","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}