{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:55:10Z","timestamp":1777888510216,"version":"3.51.4"},"reference-count":66,"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":["62406068"],"award-info":[{"award-number":["62406068"]}],"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\/iccv51701.2025.02361","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"25453-25463","source":"Crossref","is-referenced-by-count":0,"title":["UniMLVG: Unified Framework for Multi-View Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Rui","family":"Chen","sequence":"first","affiliation":[{"name":"Advanced Ocean Institute, Southeast University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zehuan","family":"Wu","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichen","family":"Liu","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Guo","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingcheng","family":"Ni","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyu","family":"Xia","sequence":"additional","affiliation":[{"name":"Advanced Ocean Institute, Southeast University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Latte: Latent diffusion transformer for video generation","volume-title":"arXiv preprint","year":"2024"},{"key":"ref2","volume-title":"Multimodal perception and comprehension of corner cases in autonomous driving","year":"2024"},{"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","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref7","article-title":"Adversarial video generation on complex datasets","author":"Clark","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"1174","article-title":"Stochastic video generation with a learned prior","volume-title":"International conference on machine learning","author":"Denton","year":"2018"},{"key":"ref9","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy","year":"2017"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref11","article-title":"Flux","volume-title":"Flux ai studio","year":"2024"},{"key":"ref12","article-title":"Magicdrive: Street view generation with diverse 3d geometry control","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_28"},{"key":"ref17","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref19","article-title":"Learning to decompose and disentangle representations for video prediction","volume":"31","author":"Hsieh","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref23","article-title":"Dive: Dit-based video generation with enhanced control","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_22"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00649"},{"key":"ref27","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref30","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Dreamforge: Motion-aware autoregressive video generation for multi-view driving scenes","author":"Mei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref33","volume-title":"Open-sora","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"140","key":"ref37","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01333-y"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897982"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0707"},{"key":"ref46","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","article-title":"Video-tovideo synthesis","author":"Wang","year":"2018","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Drivemlm: Aligning multi-modal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Drivedreamer: Towards real-worlddriven world models for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref53","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Godiva: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref57","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01113"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00618"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983149"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref64","article-title":"Real-time video generation with pyramid attention broadcast","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"}],"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\/11444182.pdf?arnumber=11444182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:46:31Z","timestamp":1777610791000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02361","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}