{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T14:44:42Z","timestamp":1783953882014,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Guangzhou Education Bureau Project","award":["2024312095"],"award-info":[{"award-number":["2024312095"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tvt.2025.3632881","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:49:03Z","timestamp":1763146143000},"page":"7469-7482","source":"Crossref","is-referenced-by-count":1,"title":["NetRoller: Interfacing General and Specialized Models for End-to-End Autonomous Driving"],"prefix":"10.1109","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9548-5076","authenticated-orcid":false,"given":"Ren","family":"Xin","sequence":"first","affiliation":[{"name":"Division of Emerging Interdisciplinary Areas, The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0272-3045","authenticated-orcid":false,"given":"Hongji","family":"Liu","sequence":"additional","affiliation":[{"name":"Division of Emerging Interdisciplinary Areas, The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4687-6345","authenticated-orcid":false,"given":"Xiaodong","family":"Mei","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5055-0884","authenticated-orcid":false,"given":"Wenru","family":"Liu","sequence":"additional","affiliation":[{"name":"Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maosheng","family":"Ye","sequence":"additional","affiliation":[{"name":"DeepRoute.ai, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8272-156X","authenticated-orcid":false,"given":"Zhili","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9405-8232","authenticated-orcid":false,"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"Division of Emerging Interdisciplinary Areas, The Hong Kong University of Science and Technology, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128800"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3341412"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3330581"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3266940"},{"key":"ref7","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-7131-2_100141"},{"key":"ref9","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref10","article-title":"The LLaMA 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref11","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2025.3525657"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.3"},{"key":"ref14","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref16","article-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving","author":"Jiang","year":"2024"},{"key":"ref17","article-title":"EMMA: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024"},{"key":"ref18","article-title":"OmniDrive: A holistic LLM-agent framework for autonomous driving with 3D perception, reasoning and planning","author":"Wang","year":"2024"},{"key":"ref19","article-title":"AlphaDrive: Unleashing the power of VLMs in autonomous driving via reinforcement learning and reasoning","author":"Jiang","year":"2025"},{"key":"ref20","article-title":"DriveMLM: Aligning multi-modal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023"},{"key":"ref21","first-page":"4698","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","volume-title":"Proc. Conf. Robot Learn.","author":"Tian","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref23","article-title":"VLM-E2E: Enhancing end-to-end autonomous driving with multimodal driver attention fusion","author":"Liu","year":"2025"},{"key":"ref24","article-title":"VLM-AD: End-to-end autonomous driving through vision-language model supervision","author":"Xu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02302"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i16.38386"},{"key":"ref29","article-title":"DSDrive: Distilling large language model for lightweight end-to-end autonomous driving with unified reasoning and planning","author":"Liu","year":"2025"},{"key":"ref30","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024"},{"key":"ref31","article-title":"Circuit tracing: Revealing computational graphs in language models","volume":"6","author":"Ameisen","year":"2025","journal-title":"Transformer Circuits Thread"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01417"},{"key":"ref34","article-title":"VADv2: End-to-end vectorized autonomous driving via probabilistic planning","author":"Chen","year":"2024"},{"key":"ref35","article-title":"PLUTO: Pushing the limit of imitation learning-based planning for autonomous driving","author":"Cheng","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01124"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/drones9040238"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3515454"},{"key":"ref44","article-title":"SmolVLM: Redefining small and efficient multimodal models","author":"Marafioti","year":"2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref47","article-title":"GPT-Driver: Learning to drive with GPT","author":"Mao","year":"2023"},{"key":"ref48","article-title":"PlanScope: Learning to plan within decision scope does matter","author":"Xin","year":"2024"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/25\/11526914\/11249682.pdf?arnumber=11249682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:52:17Z","timestamp":1779306737000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":48,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2025.3632881","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}