{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:45:48Z","timestamp":1785912348276,"version":"3.56.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":[[2026,3]]},"DOI":"10.1109\/wacvw68408.2026.00187","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:09:48Z","timestamp":1785870588000},"page":"1729-1738","source":"Crossref","is-referenced-by-count":0,"title":["FROST-Drive: Scalable and Efficient End-to-End Driving with a Frozen Vision Encoder"],"prefix":"10.1109","author":[{"given":"Zeyu","family":"Dong","sequence":"first","affiliation":[{"name":"Stony Brook University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Stony Brook University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Rutgers University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Sun","sequence":"additional","affiliation":[{"name":"Sunrise Technology Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"End to End Learning for Self-Driving Cars","author":"Bojarski","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01671"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3435937"},{"key":"ref4","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3200245"},{"key":"ref9","volume-title":"Hint-ad: Holistically aligned interpretability in end-to-end autonomous driving","author":"Ding","year":"2024"},{"key":"ref10","volume-title":"Generalizing End-To-End Autonomous Driving In Real-World Environments Using Zero-Shot LLMs","author":"Dong","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ELMAR62909.2024.10694536"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref13","volume-title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","author":"Hwang","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IS3C50286.2020.00056"},{"key":"ref17","volume-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","author":"Li","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01408"},{"key":"ref19","volume-title":"Waymo end-to-end driving dataset","year":"2025"},{"key":"ref20","volume-title":"Vision-based end-to-end driving","year":"2025"},{"key":"ref21","volume-title":"GPT- Driver: Learning to Drive with GPT","author":"Mao","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2005.309"},{"key":"ref23","article-title":"ViNG: Learning Open-World Navigation with Visual Goals","author":"Shah","year":"2020","journal-title":"arXiv.Org"},{"key":"ref24","volume-title":"LM- Nav: Robotic Navigation with Large PreTrained Models of Language, Vision, and Action","author":"Shah","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01432"},{"key":"ref26","volume-title":"Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer","author":"Shao","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01319"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21512\/commit.v17i2.8425"},{"key":"ref29","volume-title":"Car crashes rank among the leading causes of death in the united states-impact speed and a pedestrian\u2019s risk of severe injury or death","author":"Tefft","year":"2010"},{"key":"ref30","volume-title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","author":"Tian","year":"2024"},{"key":"ref31","volume-title":"DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving","author":"Wang","year":"2024"},{"key":"ref32","article-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3440097"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.075"},{"key":"ref35","volume-title":"Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes","author":"Zhai","year":"2023"},{"key":"ref36","volume-title":"AD-H: Autonomous Driving with Hierarchical Agents","author":"Zhang","year":"2024"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11617369\/11617396\/11617440.pdf?arnumber=11617440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:55:13Z","timestamp":1785909313000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11617440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/wacvw68408.2026.00187","relation":{},"subject":[],"published":{"date-parts":[[2026,3]]}}}