{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T19:12:06Z","timestamp":1778699526022,"version":"3.51.4"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/iv64158.2025.11097438","type":"proceedings-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T17:54:55Z","timestamp":1754502895000},"page":"2235-2242","source":"Crossref","is-referenced-by-count":2,"title":["Video Token Sparsification for Efficient Multimodal LLMs in Driving Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Yunsheng","family":"Ma","sequence":"first","affiliation":[{"name":"Toyota InfoTech Labs,Mountain View,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amr","family":"Abdelraouf","sequence":"additional","affiliation":[{"name":"Toyota InfoTech Labs,Mountain View,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Gupta","sequence":"additional","affiliation":[{"name":"Toyota InfoTech Labs,Mountain View,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmadreza","family":"Moradipari","sequence":"additional","affiliation":[{"name":"Toyota InfoTech Labs,Mountain View,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziran","family":"Wang","sequence":"additional","affiliation":[{"name":"Purdue University,West Lafayette,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyungtae","family":"Han","sequence":"additional","affiliation":[{"name":"Toyota InfoTech Labs,Mountain View,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref2","article-title":"Visual Instruction Tuning","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref5","article-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","author":"Wei","year":"2022","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Token Merging: Your ViT But Faster","author":"Bolya","year":"2023","journal-title":"ICLR"},{"key":"ref7","article-title":"A Language Agent for Autonomous Driving","author":"Mao","year":"2024","journal-title":"COLM"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref10","author":"Sha","year":"2023","journal-title":"LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"ref12","article-title":"DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models","author":"Wen","year":"2024","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01398"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01392"},{"key":"ref15","article-title":"LingoQA: Video Question Answering for Autonomous Driving","author":"Marcu","year":"2024","journal-title":"ECCV"},{"key":"ref16","author":"Renz","year":"2024","journal-title":"CarLLaVA: Vision language models for camera-only closed-loop driving"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02061"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.287"},{"key":"ref19","author":"Hwang","year":"2024","journal-title":"EMMA: End-to-End Multimodal Model for Autonomous Driving"},{"key":"ref20","author":"Huang","year":"2024","journal-title":"VLM-RL: A Unified Vision Language Models and Reinforcement Learning Framework for Safe Autonomous Driving"},{"key":"ref21","author":"Xing","year":"2024","journal-title":"AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC58415.2024.10919978"},{"key":"ref23","author":"Jiang","year":"2024","journal-title":"Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2024.3381793"},{"key":"ref25","article-title":"Distilling Multi-modal Large Language Models for Autonomous Driving","author":"Hegde","year":"2025","journal-title":"CVPR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00114"},{"key":"ref27","author":"Wang","year":"2024","journal-title":"OmniDrive: A Holistic LLM-Agent Framework for Autonomous Driving with 3D Perception, Reasoning and Planning"},{"key":"ref28","article-title":"Drive VLM: The Convergence of Autonomous Driving and Large Vision-Language Models","author":"Tian","year":"2024","journal-title":"CoRL"},{"key":"ref29","author":"Ma","year":"2024","journal-title":"MTA: Multimodal Task Alignment for BEV Perception and Captioning"},{"key":"ref30","article-title":"Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving","author":"Tian","year":"2024","journal-title":"CoRL"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01434"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01487"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00064"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_7"},{"key":"ref37","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref38","author":"Bai","year":"2023","journal-title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond"},{"key":"ref39","year":"2023","journal-title":"GPT-4 Technical Report"},{"key":"ref40","article-title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","author":"Chen","year":"2024","journal-title":"CVPR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref42","article-title":"Bleu: a Method for Automatic Evaluation of Machine Translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref43","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":"ref44","article-title":"ROUGE: A Package for Automatic Evaluation of Sum-maries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"ref48","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","author":"Hu","year":"2022","journal-title":"ICLR"}],"event":{"name":"2025 IEEE Intelligent Vehicles Symposium (IV)","location":"Cluj-Napoca, Romania","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11097351\/11097337\/11097438.pdf?arnumber=11097438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T04:58:40Z","timestamp":1754542720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11097438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iv64158.2025.11097438","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}