{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:42:20Z","timestamp":1779295340955,"version":"3.51.4"},"reference-count":75,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62225603,623B2038"],"award-info":[{"award-number":["62225603,623B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02302","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24823-24834","source":"Crossref","is-referenced-by-count":3,"title":["Orion: A Holistic End-To-End Autonomous Driving Framework by Vision-Language Instructed Action Generation"],"prefix":"10.1109","author":[{"given":"Haoyu","family":"Fu","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diankun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiaomi EV"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongchuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Cui","sequence":"additional","affiliation":[{"name":"Xiaomi EV"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dingkang","family":"Liang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiaomi EV"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Xie","sequence":"additional","affiliation":[{"name":"Xiaomi EV"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"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","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Gemini: A family of highly capable multimodal models","author":"Anil","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Improving image generation with better captions","author":"Betker","year":"2023","journal-title":"Computer Science."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref8","article-title":"Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction","author":"Chai","year":"1910","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Vadv2: End-to-end vectorized autonomous driving via probabilistic planning","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref12","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conf. on Robot Learning","author":"Dosovitskiy","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1205"},{"key":"ref15","first-page":"139","author":"Goodfellow","year":"2020","journal-title":"Generative adversarial networks. Communications of the ACM"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref17","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. of Intl. Conf. on Learning Representations","author":"Hu","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref20","article-title":"Emma: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00757"},{"key":"ref22","article-title":"Driveadapter: Breaking the coupling barrier of perception and planning","volume-title":"end-to-end autonomous driving. In Porc. of IEEE Intl. Conf. on Computer Vision","author":"Jia","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02105"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"},{"key":"ref25","article-title":"Drivetransformer: Unified transformer for scalable end-toend autonomous driving","volume-title":"Proc. of Intl. Conf. on Learning Representations","author":"Jia","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref27","article-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref29","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01408"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01124"},{"key":"ref34","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Annual Meeting of the Association for Computational Linguistics Workshop","author":"Lin","year":"2004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref37","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref39","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3918"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref43","article-title":"Mathbert: A pre-trained model for mathematical formula understanding","author":"Peng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00700"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. of Intl. Conf. on Machine Learning","author":"Radford","year":"2021"},{"key":"ref47","article-title":"Carllava: Vision language models for camera-only closed-loop driving","author":"Renz","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0473"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref53","article-title":"Don\u2019t shake the wheel: Momentumaware planning","volume-title":"end-to-end autonomous driving. In Proc. of IEEE Intl. Conf. on Computer Vision and Pattern Recognition","author":"Song","year":"2025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1566"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref56","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref61","article-title":"Omnidrive: A holistic llm-agent framework for autonomous driving with 3d perception, reasoning and planning","volume-title":"Proc. of IEEE Intl. Conf. on Computer Vision and Pattern Recognition","author":"Wang","year":"2024"},{"key":"ref62","article-title":"Drivemlm: Aligning multi-modal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2235"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0443"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00113"},{"key":"ref66","article-title":"Rethinking the open-loop evaluation of end-to-end autonomous driving in nuscenes","author":"Zhai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3328929"},{"key":"ref69","article-title":"Sparsead: Sparse query-centric paradigm for efficient end-to-end autonomous driving","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_6"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02582"},{"key":"ref74","article-title":"Hidden biases of end-to-end driving datasets","author":"Zimmerlin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","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\/11445650.pdf?arnumber=11445650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:43Z","timestamp":1777531603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02302","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}