{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:54:41Z","timestamp":1777888481764,"version":"3.51.4"},"reference-count":81,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00880","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9431-9442","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Yue","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Lin","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangtong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dechang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Xiong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhai","family":"Zhao","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","author":"Awadalla","year":"2023","journal-title":"Openflamingo: An opensource framework for training large autoregressive visionlanguage models"},{"issue":"2","key":"ref3","volume":"1","author":"Bai","year":"2023","journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond"},{"key":"ref4","author":"Bai","year":"2025","journal-title":"Qwen2. 5-vl technical report"},{"key":"ref5","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"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":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02061"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00699"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_2"},{"key":"ref12","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2024","journal-title":"Con-ference on Computer Vision and Pattern Recognition"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref14","author":"Ding","year":"2023","journal-title":"Hilm-d: Towards high-resolution understanding in multimodal large language models for autonomous driving"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01297"},{"key":"ref16","author":"Fu","year":"2023","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01975"},{"key":"ref19","author":"Han","year":"2021","journal-title":"Soda10m: A large-scale 2d self\/semisupervised object detection dataset for autonomous driving"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.70675\/802872a7z8092z4556za1fdz2c7af45f0e72"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6706807"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref23","author":"Huang","year":"2024","journal-title":"Drivemm: All-in-one large multimodal model for autonomous driving"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref25","author":"Jiang","year":"2024","journal-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.032"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01084"},{"key":"ref29","author":"Kotseruba","year":"2016","journal-title":"Joint attention in autonomous driving (jaad)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref31","author":"Li","year":"2024","journal-title":"Llava-onevision: Easy visual task transfer"},{"key":"ref32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_24"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref35","author":"Li","year":"2024","journal-title":"Automated evaluation of large visionlanguage models on self-driving corner cases"},{"key":"ref36","article-title":"Is ego status all you need for openloop end-to-end autonomous driving?","volume-title":"Conference on Computer Vision and Pattern Recognition","author":"Li","year":"2024"},{"key":"ref37","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref39","volume":"36","author":"Liu","year":"2023","journal-title":"Visual instruction tuning. Advances in neural information processing systems"},{"key":"ref40","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref41","article-title":"Mmbench: Is your multi-modal model an all-around player?","volume-title":"In European Conference on Computer Vision","author":"Liu","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32623"},{"key":"ref43","article-title":"Dolphins: Multimodal language model for driving","volume-title":"European Conference on Computer Vision","author":"Ma","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref45","author":"Mao","year":"2021","journal-title":"One million scenes for autonomous driving: Once dataset"},{"key":"ref46","author":"Mao","year":"2023","journal-title":"Gpt-driver: Learning to drive with gpt"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_15"},{"key":"ref48","article-title":"Med-flamingo: a multimodal medical few-shot learner","author":"Moor","year":"2023","journal-title":"Machine Learning for Health"},{"key":"ref49","article-title":"Reason2drive: Towards interpretable and chain-based reasoning for autonomous driving","volume-title":"European Conference on Computer Vision","author":"Nie","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01398"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10609989"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00107"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00636"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00734"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref59","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3274536"},{"key":"ref61","author":"Tian","year":"2024","journal-title":"Drivevlm: The convergence of autonomous driving and large vision-language models"},{"key":"ref62","author":"Tong","year":"2024","journal-title":"Cambrian1: A fully open, vision-centric exploration of multimodal 1 lms"},{"key":"ref63","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0827"},{"key":"ref66","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref67","author":"Wang","year":"2024","journal-title":"Omnidrive: A holistic llm-agent framework for autonomous driving with 3d perception, reasoning and planning"},{"key":"ref68","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2021","journal-title":"Neural Information Processing Systems Track on Datasets and Benchmarks"},{"key":"ref69","author":"Wu","year":"2024","journal-title":"Vila-u: a unified foundation model integrating visual understanding and generation"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00621"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref72","author":"Xue","year":"2024","journal-title":"Longvila: Scaling long-context visual language models for long videos"},{"key":"ref73","author":"Yao","year":"2024","journal-title":"Minicpm-v: A gpt-4v level mllm on your phone"},{"key":"ref74","author":"Ye","year":"2023","journal-title":"mplug-docowl: Modularized multimodal large language model for document understanding"},{"key":"ref75","author":"Zhai","year":"2023","journal-title":"Rethinking the open-loop evaluation of end-to-end autonomous driving in nuscenes"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref77","author":"Zhang","year":"2023","journal-title":"Internlmxcomposer: A vision-language large model for advanced text-image comprehension and composition"},{"key":"ref78","author":"Zhang","year":"2024","journal-title":"Llavanext: A strong zero-shot video understanding model"},{"key":"ref79","author":"Zhang","year":"2024","journal-title":"Mme-realworld: Could your multimodal 11 m challenge high-resolution real-world scenarios that are difficult for humans?"},{"key":"ref80","author":"Zhu","year":"2023","journal-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models"},{"key":"ref81","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Conference on Robot Learning","author":"Zitkovich","year":"2023"}],"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\/11443600.pdf?arnumber=11443600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:45:20Z","timestamp":1777610720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00880","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}