{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:46Z","timestamp":1777890166048,"version":"3.51.4"},"reference-count":74,"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\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2025A1515011434"],"award-info":[{"award-number":["2025A1515011434"]}],"id":[{"id":"10.13039\/501100021171","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\/iccv51701.2025.02656","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"28599-28609","source":"Crossref","is-referenced-by-count":0,"title":["DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Chen","family":"Shi","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoshuai","family":"Shi","sequence":"additional","affiliation":[{"name":"Didi Chuxing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kehua","family":"Sheng","sequence":"additional","affiliation":[{"name":"Didi Chuxing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Didi Chuxing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Jiang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01373"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1873"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","article-title":"Gamegen-x: Interactive open-world game video generation","author":"Che","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3200245"},{"key":"ref7","article-title":"OpenScene Contributors","volume-title":"Openscene: The largest up-todate 3d occupancy prediction benchmark in autonomous driving","year":"2023"},{"key":"ref8","article-title":"Navsim: Data-driven nonreactive autonomous vehicle simulation and benchmarking","author":"Dauner","year":"2024","journal-title":"NeurIPS"},{"key":"ref9","article-title":"Magicdrive: Street view generation with diverse 3d geometry control","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Magicdrive3d: Controllable 3d generation for any-view rendering in street scenes","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3610517"},{"key":"ref13","article-title":"Recurrent world models facilitate policy evolution","author":"Ha","year":"2018","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2020","journal-title":"ICLR"},{"key":"ref15","article-title":"Mastering atari with discrete world models","author":"Hafner","year":"2021","journal-title":"ICLR"},{"key":"ref16","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2027"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref20","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2023","journal-title":"ICLR"},{"key":"ref21","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_21"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00114"},{"key":"ref27","article-title":"Pointpillars: Fast encoders for object detection from point clouds","author":"Alex","year":"2019","journal-title":"CVPR"},{"key":"ref28","first-page":"2022","volume":"2","author":"LeCun","year":"2022","journal-title":"A path towards autonomous machine intelligence version 0.9"},{"key":"ref29","article-title":"T2v-turbo: Breaking the quality bottleneck of video consistency model with mixed reward feedback","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_6"},{"key":"ref31","article-title":"Navigation-guided sparse scene representation for end-to-end autonomous driving","author":"Li","year":"2025","journal-title":"ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_27"},{"key":"ref33","article-title":"Semi-supervised vision-centric 3d occupancy world model for autonomous driving","author":"Li","year":"2025","journal-title":"ICLR"},{"key":"ref34","article-title":"Enhancing end-to-end autonomous driving with latent world model","author":"Li","year":"2025","journal-title":"ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01408"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01124"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref40","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00620"},{"key":"ref42","article-title":"Self-supervised point cloud prediction using 3d spatio-temporal convolutional networks","author":"Mersch","year":"2022","journal-title":"CoRL"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01470"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01470"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"ref46","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Planning to explore via self-supervised world models","author":"Sekar","year":"2020","journal-title":"ICML"},{"key":"ref48","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-022-01710-9","article-title":"Pvrcnn++: Point-voxel feature set abstraction with local vector representation for 3d object detection","author":"Shi","year":"2023","journal-title":"IJCV"},{"key":"ref49","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref50","article-title":"Diffusion models are real-time game engines","author":"Valevski","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref52","article-title":"Omnidrive: A holistic llm-agent framework for autonomous driving with 3d perception, reasoning and planning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref54","article-title":"Videocomposer: Compositional video synthesis with motion controllability","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref55","article-title":"Drivedreamer: Towards real-worlddriven world models for autonomous driving","author":"Wang","year":"2024","journal-title":"ECCV"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref57","article-title":"Inverting the pose forecasting pipeline with spf2: Sequential pointcloud forecasting for sequential pose forecasting","author":"Weng","year":"2021","journal-title":"CoRL"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_32"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01463"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref61","article-title":"Pred: pre-training via semantic rendering on lidar point clouds","author":"Yang","year":"2024","journal-title":"NeurIPS"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33010"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01390"},{"key":"ref64","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2025","journal-title":"ICLR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_23"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref67","article-title":"Rethinking the open-loop evaluation of end-to-end autonomous driving in nuscenes","author":"Zhai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3567828"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref70","article-title":"Copilot4d: Learning unsupervised world models for autonomous driving via discrete diffusion","author":"Zhang","year":"2024","journal-title":"ICLR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02582"},{"key":"ref74","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"NeurIPS"}],"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\/11445660.pdf?arnumber=11445660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:23Z","timestamp":1777613543000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445660\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02656","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}