{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:01Z","timestamp":1777888681205,"version":"3.51.4"},"reference-count":49,"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\/iccv51701.2025.02542","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27380-27389","source":"Crossref","is-referenced-by-count":0,"title":["RoboTron-Sim: Improving Real-World Driving via Simulated Hard-Case"],"prefix":"10.1109","author":[{"given":"Baihui","family":"Xiao","sequence":"first","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjian","family":"Feng","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijian","family":"Huang","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Yan","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Zhong","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","volume-title":"Oasis sim v3.0 autonomous driving simulation platform","author":"Ai","year":"2023"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"issue":"5","key":"ref6","volume":"3","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 %* chatgpt quality"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812100"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01297"},{"key":"ref10","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982041"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref15","article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Drivemm: All-in-one large multimodal model for autonomous driving","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_5"},{"key":"ref19","article-title":"Emma: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Autonomy 2.0: Why is self-driving always 5 years away?","author":"Jain","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref23","article-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_9"},{"key":"ref26","article-title":"Automated evaluation of large visionlanguage models on self-driving corner cases","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01408"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0757"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref30","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref32","article-title":"Lingoqa: Video question answering for autonomous driving","volume-title":"ECCV","author":"Marcu","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"ref34","first-page":"718","article-title":"Urban driver: Learning to drive from real-world demonstrations using policy gradients","volume-title":"Conference on Robot Learning","author":"Scheel","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref38","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Omnidrive: A holistic llm-agent framework for autonomous driving with 3d perception, reasoning and planning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Dilu: A knowledge-driven approach to autonomous driving with large language models","author":"Wen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Policy pre-training for autonomous driving via self-supervised geometric modeling","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref43","article-title":"Robomm: All-in-one multimodal large model for robotic manipulation","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Llm4drive: A survey of large language models for autonomous driving","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"A survey of large language models for autonomous driving","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_24"},{"key":"ref47","article-title":"Rethinking the open-loop evaluation of end-to-end autonomous driving in nuscenes","author":"Zhai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3748302"},{"key":"ref49","article-title":"P3nav: A unified framework for embodied navigation integrating perception, planning, and prediction","author":"Zhong","year":"2025","journal-title":"arXiv preprint"}],"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\/11444934.pdf?arnumber=11444934","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:24Z","timestamp":1777611264000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444934\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02542","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}