{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:51:06Z","timestamp":1783183866285,"version":"3.54.6"},"reference-count":88,"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\/iccv51701.2025.00621","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6285-6297","source":"Crossref","is-referenced-by-count":12,"title":["Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives"],"prefix":"10.1109","author":[{"given":"Shaoyuan","family":"Xie","sequence":"first","affiliation":[{"name":"University of California,Irvine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingdong","family":"Kong","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chonghao","family":"Sima","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi Alfred","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California,Irvine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,S-Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Pan","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi3 Technical Report: A Highly Capable Language Model Locally on Your Phone","author":"Abdin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"GPT-4 Technical Report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.122"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref5","article-title":"Qwen Technical Report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.474"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00759"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"ref11","article-title":"DrivingGPT: Unifying Driving World Modeling and Planning with Multi-Modal Autoregressive Transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"InternVL: Scaling Up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1215"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00847"},{"key":"ref17","article-title":"DriveLM: Driving with Graph Visual Question Answering","volume-title":"DriveLM contributors","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2023.111741"},{"key":"ref19","first-page":"6216","article-title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-Training (CLIP)","volume-title":"International Conference on Machine Learning","author":"Fang","year":"2022"},{"key":"ref20","article-title":"VERDI: VLM-Embedded Reasoning for Autonomous Driving","author":"Feng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02302"},{"key":"ref23","article-title":"LlaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.2023.0306"},{"key":"ref25","article-title":"DriveMLLM: A Benchmark for Spatial Understanding with Multimodal Large Language Models in Autonomous Driving","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"VDT-Auto: End-to-End Autonomous Driving with VLM-Guided Diffusion Transformers","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref29","article-title":"BEVDet: High-Performance Multi-Camera 3D Object Detection in Bird-Eye-View","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_5"},{"key":"ref31","article-title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","author":"Hwang","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref33","article-title":"Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01830"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0932"},{"key":"ref37","article-title":"The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01693"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01408"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28121"},{"key":"ref44","first-page":"74","article-title":"ROUGE: A Package for Automatic Evaluation of Summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref45","article-title":"Coarse Correspondences Elicit 3D Spacetime Understanding in Multimodal Language Model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref48","author":"Liu","year":"2024","journal-title":"LLaVA-Ne XT: Improved Reasoning, OCR, and World Knowledge"},{"key":"ref49","article-title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","volume-title":"Conference on Language Modeling","author":"Liu","year":"2024"},{"key":"ref50","article-title":"Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Oryx MLLM: On-Demand Spatial- Temporal Understanding at Arbitrary Resolution","volume-title":"International Conference on Learning Representations","author":"Liu","year":"2025"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_23"},{"key":"ref53","article-title":"MTA: Multimodal Task Alignment for BEV Perception and Captioning","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref55","article-title":"GPT-Driver: Learning to Drive with GPT","author":"Mao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Foundation Models for Autonomous Systems","volume-title":"OpenDriveLab","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01398"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref60","article-title":"Adversarial ML Problems Are Getting Harder to Solve and to Evaluate","author":"Rando","year":"2025","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00734"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref64","article-title":"Open-World Object Manipulation Using Pre-Trained Vision-Language Models","author":"Stone","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref66","first-page":"4698","article-title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","volume-title":"Conference on Robot Learning","author":"Tian","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2019.00034"},{"key":"ref68","article-title":"How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs","author":"Tu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref70","article-title":"Evaluation and Analysis of Hallucination in Large Vision-Language Models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Qwen2-VL: Enhancing Vision-Language Model\u2019s Perception of the World at Any Resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02090"},{"key":"ref73","first-page":"180","article-title":"DETR3D: 3D Object Detection from Multi-View Images via 3D-to-2D Queries","volume-title":"Conference on Robot Learning","author":"Wang","year":"2022"},{"key":"ref74","article-title":"DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models","volume-title":"International Conference on Learning Representations","author":"Wen","year":"2024"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32902"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3535960"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00159"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00954"},{"key":"ref79","article-title":"VLM-AD: End-to-End Autonomous Driving Through Vision-Language Model Supervision","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_2"},{"key":"ref82","article-title":"A Survey of Large Language Models for Autonomous Driving","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref83","article-title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","volume-title":"International Conference on Learning Representations","author":"Ye","year":"2025"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2025.105457"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i16.38386"},{"key":"ref87","article-title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement FineTuning","author":"Zhou","year":"2025","journal-title":"arXiv preprint"},{"key":"ref88","first-page":"2165","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\/11444430.pdf?arnumber=11444430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:18Z","timestamp":1777611978000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00621","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}