{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:44Z","timestamp":1777888664542,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFE0210700"],"award-info":[{"award-number":["2024YFE0210700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62206172"],"award-info":[{"award-number":["62206172"]}],"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\/iccv51701.2025.02577","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27760-27770","source":"Crossref","is-referenced-by-count":0,"title":["Decoupled Diffusion Sparks Adaptive Scene Generation"],"prefix":"10.1109","author":[{"given":"Yunsong","family":"Zhou","sequence":"first","affiliation":[{"name":"OpenDriveLab at Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naisheng","family":"Ye","sequence":"additional","affiliation":[{"name":"OpenDriveLab at Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Ljungbergh","sequence":"additional","affiliation":[{"name":"Zenseact"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Li","sequence":"additional","affiliation":[{"name":"OpenDriveLab at Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiazhi","family":"Yang","sequence":"additional","affiliation":[{"name":"OpenDriveLab at Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zetong","family":"Yang","sequence":"additional","affiliation":[{"name":"GAC R&D Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongzi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoffer","family":"Petersson","sequence":"additional","affiliation":[{"name":"Zenseact"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyang","family":"Li","sequence":"additional","affiliation":[{"name":"OpenDriveLab at Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref3","article-title":"nuplan: A closed-loop ml-based planning benchmark for autonomous vehicles","author":"Caesar","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0759"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3435937"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref9","article-title":"Parting with misconceptions about learning-based vehicle motion planning","author":"Dauner","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref10","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy","year":"2017"},{"key":"ref11","article-title":"Baidu apollo em motion planner","author":"Fan","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref12","article-title":"Building a credible case for safety: Waymo\u2019s approach for the determination of absence of unreasonable risk","author":"Favaro","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160296"},{"key":"ref14","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","article-title":"Scenedm: Scene-level multi-agent trajectory generation with consistent diffusion models","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref16","first-page":"13213","article-title":"simple diffusion: End-to-end diffusion for high resolution images","volume-title":"International Conference on Machine Learning","author":"Hoogeboom","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_22"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01607"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00361"},{"key":"ref21","article-title":"Gen-drive: Enhancing diffusion generative driving policies with reward modeling and reinforcement learning finetuning","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Perceiver io: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00930"},{"key":"ref25","article-title":"Scenediffuser: Efficient and controllable driving simulation initialization and rollout","author":"Max Jiang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Scenarionet: Open-source platform for large-scale traffic scenario simulation and modeling","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3190471"},{"key":"ref28","article-title":"Drivingdiffusion: Layout-guided multi-view driving scene video generation with latent diffusion model","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00682"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01124"},{"key":"ref31","article-title":"Skill expansion and composition in parameter space","author":"Liu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_10"},{"key":"ref33","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Unleashing generalization of end-to-end autonomous driving with controllable long video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref36","first-page":"2905","article-title":"Generative skill chaining: Long-horizon skill planning with diffusion models","volume-title":"Conference on Robot Learning","author":"Mishra","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref38","volume-title":"Reward-free policy learning through active human involvement","author":"Peng","year":"2022"},{"key":"ref39","article-title":"Trajeglish: Traffic modeling as next-token prediction","volume-title":"The Twelfth International Conference on Learning Representations","author":"Philion","year":"2024"},{"key":"ref40","article-title":"The 2nd place solution for 2023 waymo open sim agents challenge","author":"Qian","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"issue":"8","key":"ref42","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref43","article-title":"CtRL-sim: Reactive and controllable driving agents with offline reinforcement learning","volume-title":"8th Annual Conference on Robot Learning","author":"Rowe","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01604"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00788"},{"key":"ref47","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Consistency models","author":"Song","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref50","article-title":"Large trajectory models are scalable motion predictors and planners","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02068"},{"key":"ref52","article-title":"Promptable closed-loop traffic simulation","author":"Tan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref53","article-title":"Language conditioned traffic generation","author":"Tan","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref54","article-title":"A framework for automated driving system testable cases and scenarios. Technical report, United States. Department of Transportation","author":"Thorn","year":"2018","journal-title":"National Highway Traffic Safety Administration"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01411"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811576"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3601553"},{"key":"ref59","article-title":"Diffusion-es: Gradient-free planning with diffusion for autonomous driving and zero-shot instruction following","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref60","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref61","article-title":"Cat: Closed-loop adversarial training for safe end-to-end driving","volume-title":"7th Annual Conference on Robot Learning","author":"Zhang","year":"2023"},{"key":"ref62","article-title":"Diffusion-based planning for autonomous driving with flexible guidance","author":"Zheng","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref63","first-page":"144","article-title":"Language-guided traffic simulation via scene-level diffusion","volume-title":"Conference on Robot Learning","author":"Zhong","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161463"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3136899"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1548"}],"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\/11444673.pdf?arnumber=11444673","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:41Z","timestamp":1777611221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444673\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02577","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}