{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:30:55Z","timestamp":1778347855660,"version":"3.51.4"},"reference-count":32,"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\/iros60139.2025.11247360","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"20501-20508","source":"Crossref","is-referenced-by-count":4,"title":["DriveLMM-o1: A Step-by-Step Reasoning Dataset and Large Multimodal Model for Driving Scenario Understanding"],"prefix":"10.1109","author":[{"given":"Ayesha","family":"Ishaq","sequence":"first","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean","family":"Lahoud","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ketan","family":"More","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Omkar","family":"Thawakar","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ritesh","family":"Thawkar","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinura","family":"Dissanayake","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noor","family":"Ahsan","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Li","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed Bin Zayed University of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01297"},{"issue":"5","key":"ref5","first-page":"4542","article-title":"Nuscenes-qa: A multi-modal visual question answering benchmark for autonomous driving scenario","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Qian"},{"key":"ref6","first-page":"27","article-title":"Commonsense reasoning for natural language processing","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts","author":"Sap"},{"key":"ref7","first-page":"3843","article-title":"Solving quantitative reasoning problems with language models","volume":"35","author":"Lewkowycz","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1487"},{"key":"ref10","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref12","first-page":"11 868","article-title":"Tell me why! explanations support learning relational and causal structure","volume-title":"International Conference on Machine Learning","author":"Lampinen"},{"key":"ref13","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1247"},{"key":"ref15","first-page":"53 728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27888"},{"key":"ref17","article-title":"Llava-o1: Let vision language models reason step-by-step","author":"Xu","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.82"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-72980-5_15","article-title":"Lingoqa: Visual question answering for autonomous driving","author":"Marcu","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_17"},{"key":"ref22","article-title":"Drivingvqa: Analyzing visual chain-of-thought reasoning of vision language models in real-world scenarios with driving theory tests","author":"Corbi\u00e8re","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421901"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.01164"},{"key":"ref25","article-title":"Roscoe: A suite of metrics for scoring step-by-step reasoning","author":"Golovneva","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.622"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i26.34987"},{"key":"ref28","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref29","article-title":"Ovis: Structural embedding alignment for multimodal large language model","author":"Lu","year":"2024"},{"key":"ref30","article-title":"Mulberry: Empowering mllm with o1-like reasoning and reflection via collective monte carlo tree search","author":"Yao","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"issue":"2","key":"ref32","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","volume":"1","author":"Hu"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247360.pdf?arnumber=11247360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:16:21Z","timestamp":1765520181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247360\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247360","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}