{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T23:29:35Z","timestamp":1782775775045,"version":"3.54.5"},"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00756","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8066-8076","source":"Crossref","is-referenced-by-count":1,"title":["NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models"],"prefix":"10.1109","author":[{"given":"Sung-Yeon","family":"Park","sequence":"first","affiliation":[{"name":"Purdue University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Can","family":"Cui","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunsheng","family":"Ma","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmadreza","family":"Moradipari","sequence":"additional","affiliation":[{"name":"Toyota InfoTech Labs"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rohit","family":"Gupta","sequence":"additional","affiliation":[{"name":"Toyota InfoTech Labs"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyungtae","family":"Han","sequence":"additional","affiliation":[{"name":"Toyota InfoTech Labs"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziran","family":"Wang","sequence":"additional","affiliation":[{"name":"Purdue University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","volume-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref4","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"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00119"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","volume-title":"Nuplan: A closed-loop ml-based planning benchmark for autonomous vehicles","author":"Caesar","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref10","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video1 lms","author":"Cheng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/wacvw60836.2024.00101"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01297"},{"key":"ref13","volume-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02245"},{"key":"ref15","article-title":"Llama-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref16","volume-title":"Multi-frame, lightweight & efficient vision-language models for question answering in autonomous driving","author":"Gopalkrishnan","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref19","volume-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref20","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Pro-ceedings of the 40th International Conference on Machine Learning. JMLR.org","author":"Li","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref22","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01434"},{"key":"ref27","volume-title":"Drama: Joint risk localization and captioning in driving","author":"Malla","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_15"},{"key":"ref29","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"OpenAI"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01398"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00107"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801870"},{"key":"ref34","volume-title":"Perception test: A diagnostic benchmark for multimodal video models","author":"P\u0103tr\u0103ucean","year":"2023"},{"key":"ref35","article-title":"Nuscenes-qa: a multi-modal visual question answering benchmark for autonomous driving scenario","volume-title":"Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence","author":"Qian","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01289"},{"key":"ref38","volume-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024"},{"key":"ref39","volume-title":"Omnidrive: A holistic llm-agent framework for autonomous driving with 3d perception, reasoning and planning","author":"Wang","year":"2024"},{"key":"ref40","volume-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2023"},{"key":"ref41","volume-title":"Occllama: An occupancy-language-action generative world model for autonomous driving","author":"Wei","year":"2024"},{"key":"ref42","volume-title":"On the road with gpt-4v(ision): Early explorations of visuallanguage model on autonomous driving","author":"Wen","year":"2023"},{"key":"ref43","article-title":"Language prompt for autonomous driving","volume":"abs\/2309.04379","author":"Wu","year":"2023","journal-title":"ArXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"ref47","article-title":"mplug-owl: Modularization empowers large language models with multimodality","volume":"abs\/2304.14178","author":"Ye","year":"2023","journal-title":"ArXiv"},{"key":"ref48","volume-title":"V2x-vlm: End-to-end v2x cooperative autonomous driving through large vision-language models","author":"You","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-95-5740-0_18"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01464"},{"key":"ref52","volume-title":"Long context transfer from language to vision","author":"Zhang","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.12.021"},{"key":"ref54","volume-title":"Llavanext: A strong zero-shot video understanding model","author":"Zhang","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_8"}],"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\/11449012.pdf?arnumber=11449012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:42Z","timestamp":1777612122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449012\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00756","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}