{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:59Z","timestamp":1777890239431,"version":"3.51.4"},"reference-count":55,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088102,U24A20291"],"award-info":[{"award-number":["62088102,U24A20291"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB4405504"],"award-info":[{"award-number":["2024YFB4405504"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.02503","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26966-26976","source":"Crossref","is-referenced-by-count":0,"title":["VLR-Driver: Large Vision-Language-Reasoning Models for Embodied Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Fanjie","family":"Kong","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitong","family":"Li","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihuang","family":"Chen","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Min","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhe","family":"Li","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Gao","sequence":"additional","affiliation":[{"name":"Engineering University of PAP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyang","family":"Li","sequence":"additional","affiliation":[{"name":"Nanchang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyu","family":"Guo","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Sun","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Letfuser: Light-weight end-to-end transformerbased sensor fusion for autonomous driving with multi-task learning","author":"Agand","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00195"},{"key":"ref3","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Detrive: Imitation learning with transformer detection for end-to-end autonomous driving","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref8","article-title":"Vadv2: End-to-end vectorized autonomous driving via probabilistic planning","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC58415.2024.10919876"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_21"},{"key":"ref14","first-page":"1","article-title":"Carla: An open urban driving simulator","author":"Dosovitskiy","year":"2017","journal-title":"CoRL"},{"key":"ref15","article-title":"Rad: Training an end-to-end driving policy via large-scale 3dgs-based reinforcement learning","author":"Gao","year":"2025","journal-title":"arXiv preprint"},{"issue":"2","key":"ref16","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00361"},{"key":"ref19","article-title":"Emma: End-to-end multimodal model for autonomous driving","author":"Hwang","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00731"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02105"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"},{"key":"ref23","article-title":"Drivetransformer: Unified transformer for scalable end-toend autonomous driving","author":"Jia","year":"2025","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref25","article-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"A survey on vision-language-action models for embodied ai","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3918"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00700"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref30","article-title":"Languagempc: Large language models as decision makers for autonomous driving","author":"Sha","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"726","article-title":"Safety-enhanced autonomous driving using interpretable sensor fusion transformer","volume-title":"Conference on Robot Learning","author":"Shao","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref33","article-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"He-drive: Human-like end-toend driving with vision language models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","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":"ref38","article-title":"Drivecot: Integrating chain-of-thought reasoning with end-to-end driving","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Drivemlm: Aligning multi-modal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0443"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3307589"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00113"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref46","article-title":"Llm4drive: A survey of large language models for autonomous driving","author":"Yang","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Fusionad: Multi-modality fusion for prediction and planning tasks of autonomous driving","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref49","article-title":"End-to-End Learning for Autonomous Driving","volume-title":"PhD thesis, New York University, USA","author":"Zhang","year":"2019"},{"key":"ref50","author":"Zhang","year":"2024","journal-title":"Llavanext: A strong zero-shot video understanding model"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3621971"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics9040248"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3402136"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_8"}],"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\/11445657.pdf?arnumber=11445657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:20Z","timestamp":1777613540000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02503","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}