{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:06:15Z","timestamp":1777889175651,"version":"3.51.4"},"reference-count":57,"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":["62206173"],"award-info":[{"award-number":["62206173"]}],"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\/iccv51701.2025.02579","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27783-27793","source":"Crossref","is-referenced-by-count":0,"title":["ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Yuhang","family":"Lu","sequence":"first","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiadong","family":"Tu","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexin","family":"Ma","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinge","family":"Zhu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611018"},{"key":"ref6","article-title":"Vadv2: End-to-end vectorized autonomous driving via probabilistic planning","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_14"},{"key":"ref8","article-title":"Deepseek llm: Scaling open-source language models with longtermism","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01395"},{"key":"ref10","volume-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","year":"2024"},{"key":"ref11","article-title":"End-to-end autonomous driving without costly modularization and 3d manual annotation","author":"Guo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01254"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref16","article-title":"Drivegpt: Scaling autoregressive behavior models for driving","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_5"},{"key":"ref18","article-title":"Emma: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref21","article-title":"Senna: Bridging large vision-language models and end-to-end autonomous driving","author":"Jiang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_21"},{"key":"ref23","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref24","article-title":"Does end-to-end autonomous driving really need perception tasks?","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref25","article-title":"Enhancing end-to-end autonomous driving with latent world model","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01124"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC57777.2023.10421993"},{"key":"ref30","first-page":"403","article-title":"Dolphins: Multimodal language model for driving","volume-title":"ECCV","author":"Ma","year":"2024"},{"key":"ref31","article-title":"Gpt-driver: Learning to drive with gpt","author":"Mao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"A language agent for autonomous driving","author":"Mao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01398"},{"key":"ref34","volume-title":"Bezier curve fitting. PhD thesis","author":"Pastva","year":"1998"},{"key":"ref35","article-title":"Fasionad: Fast and slow fusion thinking systems for human-like autonomous driving with adaptive feedback","author":"Qian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Languagempc: Large language models as decision makers for autonomous driving","author":"Sha","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128800"},{"key":"ref40","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Tokenize the world into object-level knowledge to address long-tail events in autonomous driving","author":"Tian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref44","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 arXiv"},{"key":"ref45","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref46","article-title":"Drivemlm: Aligning multi-modal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Dilu: A knowledge-driven approach to autonomous driving with large language models","author":"Wen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01463"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0443"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/wacvw65960.2025.00113"},{"key":"ref51","article-title":"Vlm-ad: End-to-end autonomous driving through vision-language model supervision","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref53","article-title":"Yi: Open foundation models by 01. ai","author":"Young","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","article-title":"Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref56","article-title":"Rethinking the open-loop evaluation of end-to-end autonomous driving in nuscenes","author":"Zhai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_6"}],"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\/11445064.pdf?arnumber=11445064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:49Z","timestamp":1777612069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02579","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}