{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T16:17:56Z","timestamp":1779207476924,"version":"3.51.4"},"reference-count":87,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/iv64158.2025.11097718","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:54:55Z","timestamp":1754502895000},"page":"2243-2250","source":"Crossref","is-referenced-by-count":4,"title":["MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representations"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Bogdoll","sequence":"first","affiliation":[{"name":"FZI Research Center for Information Technology,Germany"}]},{"given":"Yitian","family":"Yang","sequence":"additional","affiliation":[{"name":"FZI Research Center for Information Technology,Germany"}]},{"given":"Tim","family":"Joseph","sequence":"additional","affiliation":[{"name":"FZI Research Center for Information Technology,Germany"}]},{"given":"Melih","family":"Yazgan","sequence":"additional","affiliation":[{"name":"FZI Research Center for Information Technology,Germany"}]},{"given":"J. Marius","family":"Zollner","sequence":"additional","affiliation":[{"name":"FZI Research Center for Information Technology,Germany"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv"},{"key":"ref2","article-title":"Genie: Generative interactive environments","author":"Bruce","year":"2024","journal-title":"arXiv"},{"key":"ref3","author":"Parker-Holder","year":"2024","journal-title":"Genie 2: A large-scale foundation world model"},{"key":"ref4","article-title":"Hermes: A unified self-driving world model for simultaneous 3d scene understanding and generation","author":"Zhou","year":"2025","journal-title":"arXiv"},{"key":"ref5","article-title":"Unleashing generalization of end-to-end autonomous driving with controllable long video generation","author":"Ma","year":"2024","journal-title":"arXiv"},{"key":"ref6","article-title":"Mitigating covariate shift in imitation learning for autonomous vehicles using latent space generative world models","author":"Popov","year":"2024","journal-title":"arXiv"},{"key":"ref7","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","journal-title":"NeurIPS, 2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref10","article-title":"GAIA-I: A Generative World Model for Autonomous Driving","author":"Hu","year":"2023","journal-title":"arXiv"},{"key":"ref11","article-title":"Foundation Models for Autonomy","volume-title":"2023, CVPR Workshop on Autonomous Driving","author":"Elluswamy"},{"key":"ref12","article-title":"Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion","author":"Zhang","journal-title":"ICLR, 2024"},{"key":"ref13","article-title":"Trend: Unsupervised 3d representation learning via temporal forecasting for lidar perception","author":"Chen","year":"2024","journal-title":"arXiv"},{"key":"ref14","article-title":"Lidardm: Generative lidar simulation in a generated world","author":"Zyrianov","year":"2024","journal-title":"arXiv"},{"key":"ref15","article-title":"Bevworld: A multimodal world model for autonomous driving via unified bev latent space","author":"Zhang","year":"2024","journal-title":"arXiv"},{"key":"ref16","article-title":"Holodrive: Holistic 2d-3d multi-modal street scene generation for autonomous driving","author":"Wu","year":"2024","journal-title":"arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33010"},{"key":"ref18","article-title":"Occsora: 4d occupancy generation models as world simulators for autonomous driving","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681293"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3200245"},{"key":"ref22","article-title":"A Path Towards Autonomous Machine Intelligence","author":"LeCun","year":"2022","journal-title":"OpenReview:BZ5a1 r-kVsf"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI52147.2023.10371887"},{"key":"ref24","article-title":"Model-Based Imitation Learning for Urban Driving","author":"Hu","journal-title":"NeurIPS, 2022"},{"key":"ref25","article-title":"Adawm: Adaptive world model based planning for autonomous driving","author":"Wang","journal-title":"ICLR, 2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3400227"},{"key":"ref27","article-title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref29","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref30","article-title":"Mastering Diverse Domains through World Models","author":"Hafner","year":"2023","journal-title":"arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"ref32","article-title":"Day-dreamer: World models for physical robot learning","author":"Wu","journal-title":"CoRL, 2022"},{"key":"ref33","article-title":"Mastering Atari with Discrete World Models","author":"Hafner","journal-title":"ICLR, 2021"},{"key":"ref34","article-title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","author":"Chen","journal-title":"NeurIPS, 2021"},{"key":"ref35","article-title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","author":"Janner","journal-title":"NeurIPS, 2021"},{"key":"ref36","article-title":"Transformers are Sample-Efficient World Models","author":"Micheli","journal-title":"ICLR, 2022"},{"key":"ref37","article-title":"A Generalist Agent","author":"Reed","journal-title":"TMLR, 2022"},{"key":"ref38","article-title":"Masked Autoencoding for Scalable and Generalizable Decision Making","author":"Liu","journal-title":"NeurIPS, 2023"},{"key":"ref39","article-title":"Masked trajectory models for prediction, representation, and control","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref40","year":"2023","journal-title":"Commavq: A dataset of tokenized driving video and a GPT model"},{"key":"ref41","article-title":"Neural Discrete Representation Learning","volume":"30","author":"van den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01915"},{"key":"ref46","article-title":"Oc-cDepth: A Depth-Aware Method for 3D Semantic Scene Completion","author":"Miao","year":"2023","journal-title":"arXiv"},{"key":"ref47","article-title":"FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation","author":"Li","year":"2023","journal-title":"CVP RW"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref50","article-title":"MiLO: Multi-task Learning with Localization Ambiguity Suppression for Occupancy Prediction","author":"Vu","year":"2023","journal-title":"CVP RW"},{"key":"ref51","article-title":"Occupancy Networks","volume-title":"CVPR Workshop on Autonomous Driving","author":"Elluswamy","year":"2023"},{"key":"ref52","article-title":"PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095302"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16419"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00861"},{"key":"ref57","article-title":"Ren-derOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision","author":"Pan","year":"2023","journal-title":"arXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00876"},{"key":"ref59","article-title":"UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Ren-dering","author":"Pan","journal-title":"CVPRW, 2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3262139"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00133"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref63","volume-title":"Openscene: The largest up-to-date 3d occupancy prediction benchmark in autonomous driving","author":"Contributors","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00114"},{"key":"ref65","article-title":"LiDAR-based 4D Occupancy Completion and Forecasting","author":"Liu","year":"2023","journal-title":"arXiv"},{"key":"ref66","article-title":"UniWorld: Au-tonomous Driving Pre-training via World Models","author":"Chen","year":"2023","journal-title":"arXiv"},{"key":"ref67","article-title":"An efficient occupancy world model via decoupled dynamic flow and image-assisted training","author":"Zhang","year":"2024","journal-title":"arXiv"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01390"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3046646"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2016.xii.042"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref75","volume-title":"Introducing the 5th-generation waymo driver","year":"2020"},{"key":"ref76","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"Dosovitskiy","journal-title":"ICLR, 2020"},{"key":"ref77","article-title":"Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer","author":"Shao","journal-title":"CoRL, 2022"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref80","article-title":"Dream to Control: Learning Behaviors by Latent Imagination","author":"Hafner","journal-title":"ICLR, 2020"},{"key":"ref81","article-title":"Recurrent world models facilitate policy evolution","author":"Ha","journal-title":"NeurIPS, 2018"},{"key":"ref82","article-title":"CARLA: An open urban driving simulator","author":"Dosovitskiy","year":"2017","journal-title":"CoRL"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref84","article-title":"Sense, Imagine, Act: Multimodal Perception Improves Model-Based Reinforcement Learning for Head-to-Head Autonomous Racing","author":"Shrestha","year":"2023","journal-title":"arXiv"},{"key":"ref85","article-title":"BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework","author":"Liang","journal-title":"NeurIPS, 2022"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref87","article-title":"Separable self-attention for mobile vision transformers","author":"Mehta","year":"2022","journal-title":"TMLR"}],"event":{"name":"2025 IEEE Intelligent Vehicles Symposium (IV)","location":"Cluj-Napoca, Romania","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11097351\/11097337\/11097718.pdf?arnumber=11097718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T04:59:37Z","timestamp":1754542777000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11097718\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/iv64158.2025.11097718","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}