{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:36Z","timestamp":1777890276921,"version":"3.51.4"},"reference-count":43,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206172"],"award-info":[{"award-number":["62206172"]}],"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\/iccv51701.2025.02462","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26529-26538","source":"Crossref","is-referenced-by-count":0,"title":["ETA: Efficiency through Thinking Ahead, a Dual Approach to Self-Driving with Large Models"],"prefix":"10.1109","author":[{"given":"Shadi","family":"Hamdan","sequence":"first","affiliation":[{"name":"Koç University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chonghao","family":"Sima","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zetong","family":"Yang","sequence":"additional","affiliation":[{"name":"OpenDriveLab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyang","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatma","family":"G\u00fcney","sequence":"additional","affiliation":[{"name":"Koç University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Validity learning on failures: Mitigating the distribution shift in autonomous vehicle planning","author":"Arasteh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","volume-title":"PDM-Lite: A rule-based planner for carla leaderboard 2.0","author":"Bei\u00dfwenger","year":"2024"},{"key":"ref3","article-title":"Towards synergistic, generalized, and efficient dual-system for robotic manipulation","author":"Bu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref5","article-title":"InternVL: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"CVPR","author":"Chen","year":"2024"},{"key":"ref6","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","year":"2021"},{"key":"ref7","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"ICML","author":"Driess","year":"2023"},{"key":"ref8","volume-title":"Figure. Helix: A vision-language-action model for generalist humanoid control","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00757"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00731"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02105"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"},{"key":"ref14","article-title":"DriveTransformer: unified transformer for scalable end-toend autonomous driving","volume-title":"ICLR","author":"Jia","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref16","article-title":"Thinking, fast and slow","volume-title":"Farrar, Straus and Giroux","author":"Kahneman","year":"2011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831409"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"ref19","article-title":"Think2Drive: efficient reinforcement learning by thinking in latent world model for quasi-realistic autonomous driving (in carla-v2)","volume-title":"ECCV","author":"Li","year":"2024"},{"key":"ref20","article-title":"CogACT: a foundational vision-languageaction model for synergizing cognition and action in robotic manipulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Enhancing end-to-end autonomous driving with latent world model","volume-title":"ICLR","author":"Li","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref24","article-title":"Gpt-driver: Learning to drive with gpt","author":"Mao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Continuously learning, adapting, and improving: A dualprocess approach to autonomous driving","volume-title":"NeurIPS","author":"Mei","year":"2024"},{"key":"ref26","volume-title":"OpenAI: Introducing ChatGPT","year":"2022"},{"key":"ref27","article-title":"CarLLaVA: Vision language models for camera-only closed-loop driving","author":"Renz","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801683"},{"key":"ref30","article-title":"Hi Robot: Open-ended instruction following with hierarchical vision-language-action models","author":"Shi","year":"2025","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref32","article-title":"Centaur: Robust end-to-end autonomous driving with test-time training","author":"Sima","year":"2025","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","volume-title":"CoRL","author":"Tian","year":"2024"},{"key":"ref34","article-title":"DriveMLM: Aligning multimodal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Trajectory-guided control prediction for end-to-end autonomous driving: A simple yet strong baseline","volume-title":"NeurIPS","author":"Wu","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref37","article-title":"Distilling system 2 into system 1","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Rethinking the open-loop evaluation of end-to-end autonomous driving in nuscenes","author":"Zhai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"HiRT: Enhancing robotic control with hierarchical robot transformers","volume-title":"CoRL","author":"Zhang","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01421"},{"key":"ref41","article-title":"AD-H: autonomous driving with hierarchical agents","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Hidden biases of end-to-end driving datasets","author":"Zimmerlin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"CoRL","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\/11449039.pdf?arnumber=11449039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:48Z","timestamp":1777613628000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02462","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}