{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:21:29Z","timestamp":1765520489088,"version":"3.48.0"},"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\/iros60139.2025.11247678","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"8934-8941","source":"Crossref","is-referenced-by-count":0,"title":["Drive&Gen: Co-Evaluating End-to-End Driving and Video Generation Models"],"prefix":"10.1109","author":[{"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[{"name":"Johns Hopkins University. Work Done at Waymo"}]},{"given":"Zhenpei","family":"Yang","sequence":"additional","affiliation":[{"name":"Waymo"}]},{"given":"Yijing","family":"Bai","sequence":"additional","affiliation":[{"name":"Waymo"}]},{"given":"Yingwei","family":"Li","sequence":"additional","affiliation":[{"name":"Waymo"}]},{"given":"Yuliang","family":"Zou","sequence":"additional","affiliation":[{"name":"Waymo"}]},{"given":"Bo","family":"Sun","sequence":"additional","affiliation":[{"name":"Waymo"}]},{"given":"Abhijit","family":"Kundu","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Jose","family":"Lezama","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Luna Yue","family":"Huang","sequence":"additional","affiliation":[{"name":"Waymo"}]},{"given":"Zehao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Waymo"}]},{"given":"Jyh-Jing","family":"Hwang","sequence":"additional","affiliation":[{"name":"Waymo"}]},{"given":"Dragomir","family":"Anguelov","sequence":"additional","affiliation":[{"name":"Waymo"}]},{"given":"Mingxing","family":"Tan","sequence":"additional","affiliation":[{"name":"Waymo"}]},{"given":"Chiyu Max","family":"Jiang","sequence":"additional","affiliation":[{"name":"Waymo"}]}],"member":"263","reference":[{"article-title":"Emma: End-to-end multimodal model for autonomous driving","year":"2024","author":"Hwang","key":"ref1"},{"article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","year":"2024","author":"Tian","key":"ref2"},{"key":"ref3","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref4","first-page":"8","article-title":"Video generation models as world simulators","volume":"1","author":"Brooks","year":"2024","journal-title":"OpenAI Blog"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"article-title":"Explaining and harnessing adversarial examples","year":"2014","author":"Goodfellow","key":"ref6"},{"key":"ref7","article-title":"The waymo open sim agents challenge","author":"Montali","year":"2023","journal-title":"NeurIPS"},{"article-title":"A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27","year":"2022","author":"LeCun","key":"ref8"},{"key":"ref9","article-title":"Recurrent world models facilitate policy evolution","author":"Ha","year":"2018","journal-title":"NeurIPS"},{"article-title":"Dream to control: Learning behaviors by latent imagination","year":"2019","author":"Hafner","key":"ref10"},{"article-title":"Mastering atari with discrete world models","volume-title":"ICLR","author":"Hafner","key":"ref11"},{"article-title":"Mastering diverse domains through world models","year":"2023","author":"Hafner","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00131"},{"article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"ICLR","author":"Singer","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","year":"2023","author":"Blattmann","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"article-title":"Gaia-1: A generative world model for autonomous driving","year":"2023","author":"Hu","key":"ref19"},{"article-title":"Unleashing generalization of end-to-end autonomous driving with controllable long video generation","year":"2024","author":"Ma","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref24","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_27"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"article-title":"Magicdrive: Street view generation with diverse 3d geometry control","volume-title":"ICLR","author":"Gao","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1411-7"},{"article-title":"Gan augmentation: Augmenting training data using generative adversarial networks","year":"2018","author":"Bowles","key":"ref30"},{"article-title":"Generating images with 3d annotations using diffusion models","volume-title":"ICLR","author":"Ma","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01417"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"article-title":"Omnidrive: A holistic llm-agent framework for autonomous driving with 3d perception, reasoning and planning","year":"2024","author":"Wang","key":"ref39"},{"article-title":"Is a 3d-tokenized llm the key to reliable autonomous driving?","year":"2024","author":"Bai","key":"ref40"},{"key":"ref41","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01368"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"article-title":"Towards accurate generative models of video: A new metric & challenges","year":"2018","author":"Unterthiner","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160609"},{"article-title":"Perceiver io: A general architecture for structured inputs & outputs","volume-title":"ICLR","author":"Jaegle","key":"ref48"},{"article-title":"Zero123++: a single image to consistent multi-view diffusion base model","year":"2023","author":"Shi","key":"ref49"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247678.pdf?arnumber=11247678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:18:06Z","timestamp":1765520286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247678","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}