{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T18:46:22Z","timestamp":1785955582837,"version":"3.56.0"},"reference-count":41,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFB3908503"],"award-info":[{"award-number":["2024YFB3908503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322608"],"award-info":[{"award-number":["62322608"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00486","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5112-5121","source":"Crossref","is-referenced-by-count":3,"title":["Adadrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Ruifei","family":"Zhang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junlin","family":"Xie","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Baidu Inc.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weikai","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Tan","sequence":"additional","affiliation":[{"name":"Baidu Inc.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Wan","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01417"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/robotics12050127"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00942"},{"key":"ref6","first-page":"2990","article-title":"Group equivariant convolutional networks","volume-title":"International conference on machine learning","author":"Cohen","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197408"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref11","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_36"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref14","article-title":"Vista-llama: Reliable video narrator via equal distance to visual tokens","author":"Ma","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref15","article-title":"Gpt-driver: Learning to drive with gpt","author":"Mao","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref16","article-title":"A language agent for autonomous driving","author":"Mao","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_17"},{"key":"ref18","volume-title":"Hello gpt-4o","year":"2024"},{"key":"ref19","article-title":"Streaming long video understanding with large language models","author":"Qian","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01432"},{"key":"ref22","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01319"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref25","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"ref27","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","article-title":"Drivemlm: Aligning multi-modal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3440097"},{"key":"ref31","article-title":"Flash-vstream: Memorybased real-time understanding for long video streams","author":"Zhang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10857"},{"key":"ref33","article-title":"Tinyllama: An open-source small language model","author":"Zhang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_9"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"19","DOI":"10.3390\/opt3010003","volume":"3","author":"Zhang","year":"2022","journal-title":"Opt: Open pre-trained transformer language models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3485644"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref38","article-title":"Ad-h: Autonomous driving with hierarchical agents","author":"Zhang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01727"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33194"}],"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\/11445384.pdf?arnumber=11445384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:11Z","timestamp":1777613531000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00486","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}