{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:03:29Z","timestamp":1775595809140,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Autonomous Intelligent Unmanned Systems"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tnnls.2025.3626711","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:38:05Z","timestamp":1764873485000},"page":"1963-1977","source":"Crossref","is-referenced-by-count":2,"title":["LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8135-9012","authenticated-orcid":false,"given":"Yukai","family":"Ma","sequence":"first","affiliation":[{"name":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6612-0982","authenticated-orcid":false,"given":"Tiantian","family":"Wei","sequence":"additional","affiliation":[{"name":"TUM School of Engineering and Design, Technical University of Munich, Munich, Germany"}]},{"given":"Naiting","family":"Zhong","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3849-2736","authenticated-orcid":false,"given":"Jianbiao","family":"Mei","sequence":"additional","affiliation":[{"name":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5565-5524","authenticated-orcid":false,"given":"Tao","family":"Hu","sequence":"additional","affiliation":[{"name":"Science Island Branch of the Graduate School, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2707-3165","authenticated-orcid":false,"given":"Licheng","family":"Wen","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}]},{"given":"Xuemeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3677-7252","authenticated-orcid":false,"given":"Botian","family":"Shi","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-8939","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref3","article-title":"RAG-driver: Generalisable driving explanations with retrieval-augmented in-context learning in multi-modal large language model","author":"Yuan","year":"2024","journal-title":"arXiv:2402.10828"},{"key":"ref4","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv:2402.12289"},{"key":"ref5","article-title":"Is ego status all you need for open-loop end-to-end autonomous driving?","author":"Li","year":"2023","journal-title":"arXiv:2312.03031"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1745691612460685"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(74)90017-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3918"},{"key":"ref9","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. robot Learn.","author":"Dosovitskiy"},{"key":"ref10","article-title":"DriveArena: A closed-loop generative simulation platform for autonomous driving","author":"Yang","year":"2024","journal-title":"arXiv:2408.00415"},{"key":"ref11","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref12","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref14","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref15","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref17","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref19","article-title":"LLaVA-grounding: Grounded visual chat with large multimodal models","author":"Zhang","year":"2023","journal-title":"arXiv:2312.02949"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref22","first-page":"20165","article-title":"DiLu: A knowledge-driven approach to autonomous driving with large language models","volume-title":"Proc. ICLR","author":"Wen"},{"key":"ref23","article-title":"Drivelm: Driving with graph visual question answering","author":"Sima","year":"2023","journal-title":"arXiv:2312.14150"},{"key":"ref24","article-title":"DriveMLM: Aligning multi-modal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv:2312.09245"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10422219"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2023.07.006"},{"key":"ref30","article-title":"Building and testing a general intelligence embodied in a humanoid robot","author":"Gildert","year":"2023","journal-title":"arXiv:2307.16770"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3449-x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref34","article-title":"Lingo-1: Exploring natural language for autonomous driving","volume-title":"Wayve","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00476"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00734"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref40","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref41","first-page":"726","article-title":"Safety-enhanced autonomous driving using interpretable sensor fusion transformer","volume-title":"Proc. Conf. Robot Learn.","author":"Shao"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01530"},{"key":"ref46","first-page":"66","article-title":"Learning by cheating","volume-title":"Proc. Conf. Robot Learn.","author":"Chen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref49","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02105"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0443"},{"key":"ref52","article-title":"Text and code embeddings by contrastive pre-training","author":"Neelakantan","year":"2022","journal-title":"arXiv:2201.10005"},{"key":"ref53","article-title":"NAVSIM: Data-driven non-reactive autonomous vehicle simulation and benchmarking","author":"Dauner","year":"2024","journal-title":"arXiv:2406.15349"},{"key":"ref54","first-page":"2579","article-title":"Visualizing data using t-SNE journal of machine learning research","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.65109\/uwgl4651"},{"key":"ref56","article-title":"DriveCoT: Integrating chain-of-thought reasoning with end-to-end driving","author":"Wang","year":"2024","journal-title":"arXiv:2403.16996"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11475606\/11277258.pdf?arnumber=11277258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:00:50Z","timestamp":1775592050000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11277258\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":57,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3626711","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}