{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:11:12Z","timestamp":1778080272122,"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"}],"funder":[{"DOI":"10.13039\/501100004853","name":"CUHK","doi-asserted-by":"publisher","award":["7106937,8601130,8601440"],"award-info":[{"award-number":["7106937,8601130,8601440"]}],"id":[{"id":"10.13039\/501100004853","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\/iccv51701.2025.02612","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"28135-28144","source":"Crossref","is-referenced-by-count":1,"title":["MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control"],"prefix":"10.1109","author":[{"given":"Ruiyuan","family":"Gao","sequence":"first","affiliation":[{"name":"CUHK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xiao","sequence":"additional","affiliation":[{"name":"Huawei Cloud"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lanqing","family":"Hong","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenguo","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Xu","sequence":"additional","affiliation":[{"name":"CUHK"}],"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":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref6","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen","year":"2024"},{"key":"ref7","article-title":"ECCV 2024 W-CODA: 1st workshop on multimodal perception and comprehension of corner cases in autonomous driving","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref9","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref11","article-title":"Magicdrive3d: Controllable 3d generation for any-view rendering in street scenes","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Magicdrive: Street view generation with diverse 3d geometry control","volume-title":"ICLR","author":"Gao","year":"2024"},{"key":"ref13","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref15","article-title":"Fleet. Video diffusion models","volume-title":"NeurIPS","author":"Ho","year":"2022"},{"key":"ref16","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref18","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Dive: Dit-based video generation with enhanced control","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00349"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0757"},{"key":"ref23","article-title":"Flow matching for generative modeling","volume-title":"ICLR","author":"Lipman","year":"2023"},{"key":"ref24","article-title":"Flow matching for generative modeling","volume-title":"ICLR","author":"Lipman","year":"2023"},{"key":"ref25","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"ICLR","author":"Liu","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref27","article-title":"Unleashing generalization of end-to-end autonomous driving with controllable long video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"ICLR","author":"Meng","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref30","volume-title":"Cosmos-drive-dreams: Scalable synthetic driving data generation with world foundation models","author":"Ren","year":"2025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"ICLR","author":"Song","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref35","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Drivedreamer: Towards real-worlddriven world models for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00926"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00692"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref41","article-title":"Bevcontrol: Accurately controlling streetview elements with multi-perspective consistency via bev sketch layout","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Drivearena: A closed-loop generative simulation platform for autonomous driving","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref45","article-title":"Drivedreamer4d: World models are effective data machines for 4d driving scene representation","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref47","volume-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00383"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"}],"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\/11445591.pdf?arnumber=11445591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:17:36Z","timestamp":1777612656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445591\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02612","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}