{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:37Z","timestamp":1777865317284,"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":["62271466"],"award-info":[{"award-number":["62271466"]}],"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":["2023YFF0716500"],"award-info":[{"award-number":["2023YFF0716500"]}],"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\/iccv51701.2025.00582","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6165-6175","source":"Crossref","is-referenced-by-count":0,"title":["Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Hao","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanning","family":"Gao","sequence":"additional","affiliation":[{"name":"DeepRoute.AI,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhili","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maosheng","family":"Ye","sequence":"additional","affiliation":[{"name":"DeepRoute.AI,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongyi","family":"Cao","sequence":"additional","affiliation":[{"name":"DeepRoute.AI,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honggang","family":"Qi","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"issue":"2","key":"ref4","first-page":"3","volume":"1","author":"Bai","year":"2023","journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond"},{"key":"ref5","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee","year":"2005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref10","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 \\%^{*} chatgpt quality"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611485"},{"issue":"240","key":"ref12","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref15","author":"Ding","year":"2024","journal-title":"Hint-ad: Holistically aligned interpretability in end-to-end autonomous driving"},{"key":"ref16","author":"Dosovitskiy","journal-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01315"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref19","author":"Hu","year":"2023","journal-title":"Gaia-1: A generative world model for autonomous driving"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref22","first-page":"18893","article-title":"Pix2struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"International Conference on Machine Learning","author":"Lee","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref24","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref25","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device $\\operatorname{llm}$ compression and acceleration","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Lin","year":"2024"},{"key":"ref26","author":"Lin","year":"2023","journal-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref28","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref30","author":"Liu","year":"2024","journal-title":"Oryx mllm: On-demand spatial-temporal understanding at arbitrary resolution"},{"key":"ref31","author":"Lu","year":"2024","journal-title":"Deepseek-vl: towards real-world visionlanguage understanding"},{"key":"ref32","author":"Ma","year":"2024","journal-title":"Video token sparsification for efficient multimodal 11 ms in autonomous driving"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref34","author":"Mao","year":"2023","journal-title":"Gpt-driver: Learning to drive with gpt"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_15"},{"key":"ref36","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104327"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1330"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref44","author":"Tian","year":"2024","journal-title":"Tokenize the world into object-level knowledge to address long-tail events in autonomous driving"},{"key":"ref45","author":"Tian","year":"2024","journal-title":"Drivevlm: The convergence of autonomous driving and large vision-language models"},{"key":"ref46","author":"Tong","year":"2024","journal-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal llms"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00914"},{"key":"ref48","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref49","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref51","author":"Wang","year":"2023","journal-title":"Cogvlm: Visual expert for pretrained language models"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"issue":"1","key":"ref54","first-page":"1","volume":"9","author":"Yang","year":"2023","journal-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)"},{"key":"ref55","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models"}],"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\/11445713.pdf?arnumber=11445713","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:39Z","timestamp":1777529739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445713\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00582","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}