{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:35:46Z","timestamp":1784133346453,"version":"3.55.0"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015599","name":"Toyota Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015599","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/lra.2025.3608656","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:48:41Z","timestamp":1757526521000},"page":"11403-11410","source":"Crossref","is-referenced-by-count":4,"title":["Probing Multimodal LLMs as World Models for Driving"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3105-7624","authenticated-orcid":false,"given":"Shiva","family":"Sreeram","sequence":"first","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7259-5686","authenticated-orcid":false,"given":"Tsun-Hsuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3800-9460","authenticated-orcid":false,"given":"Alaa","family":"Maalouf","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Haifa, Haifa, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9334-1706","authenticated-orcid":false,"given":"Guy","family":"Rosman","sequence":"additional","affiliation":[{"name":"Toyota Research Institute, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2225-7275","authenticated-orcid":false,"given":"Sertac","family":"Karaman","sequence":"additional","affiliation":[{"name":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5473-3566","authenticated-orcid":false,"given":"Daniela","family":"Rus","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Hello GPT-4o","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3649506"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611590"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00108"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref9","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref10","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref11","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63596-0_10"},{"key":"ref14","first-page":"31199","article-title":"Pre-trained language models for interactive decision-making","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Li","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.703"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-101119-071628"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.066"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3366013"},{"key":"ref21","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref23","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref24","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Ramesh","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01084"},{"key":"ref26","article-title":"Language conditioned traffic generation","author":"Tan","year":"2023"},{"key":"ref27","first-page":"144","article-title":"Language-guided traffic simulation via scene-level diffusion","volume-title":"Proc. 7th Conf. Robot Learn.","author":"Zhong","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3122865"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127950"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2024.3381793"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967929"},{"key":"ref33","article-title":"ALT-Pilot: Autonomous navigation with language augmented topometric maps","author":"Omama","year":"2023"},{"key":"ref34","first-page":"34153","article-title":"Describe, explain, plan and select: Interactive planning with LLMs enables open-world multi-task agents","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2023"},{"key":"ref35","article-title":"LanguageMPC: Large language models as decision makers for autonomous driving","author":"Sha","year":"2023"},{"key":"ref36","article-title":"Drake: Model-based design and verification for robotics","author":"Tedrake","year":"2019"},{"key":"ref37","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"Dosovitskiy","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812276"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s42154-025-00364-w"},{"key":"ref41","first-page":"91240","article-title":"ReGen: Generative robot simulation via inverse design","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Nguyen","year":"2025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00715"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00140"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01026"},{"key":"ref45","first-page":"3894","article-title":"ScenarioNet: Open-source platform for large-scale traffic scenario simulation and modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_6"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2005.847331"},{"key":"ref49","volume-title":"Feedback Systems: An Introduction for Scientists and Engineers","author":"strm","year":"2010"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20244"},{"key":"ref52","article-title":"Reading videos with GPT4V","year":"2023"},{"key":"ref53","article-title":"Grid: Omni visual generation","author":"Wan","year":"2025"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11169302\/11155145.pdf?arnumber=11155145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:12:47Z","timestamp":1759295567000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11155145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":53,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3608656","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}