{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:15:40Z","timestamp":1787012140658,"version":"build-2736575974"},"reference-count":77,"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\/iccv51701.2025.02496","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26890-26900","source":"Crossref","is-referenced-by-count":2,"title":["DrivingGPT: Unifying Driving World Modeling and Planning with Multi-Modal Autoregressive Transformers"],"prefix":"10.1109","author":[{"given":"Yuntao","family":"Chen","sequence":"first","affiliation":[{"name":"HKISI, CAS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref2","first-page":"3","author":"Bojarski","year":"2016","journal-title":"End to end learning for self-driving cars"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref4","first-page":"2","author":"Brohan","year":"2023","journal-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control"},{"key":"ref5","first-page":"2","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","author":"Caesar","year":"2021","journal-title":"nuplan: A closed-loop ml-based planning benchmark for autonomous vehicles"},{"key":"ref8","first-page":"2","author":"Cheang","year":"2024","journal-title":"Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2314"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref11","first-page":"3","author":"Chen","year":"2024","journal-title":"Vadv2: End-to-end vectorized autonomous driving via probabilistic planning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref15","author":"Dauner","year":"2024","journal-title":"Navsim: Data-driven non-reactive autonomous vehicle simulation and benchmarking"},{"key":"ref16","first-page":"2","author":"Devlin","year":"2018","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref17","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref19","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref21","first-page":"2","author":"Gu","year":"2024","journal-title":"Dome: Taming diffusion model into high-fidelity controllable occupancy world model"},{"key":"ref22","first-page":"3","article-title":"Waymax: An accelerated, data-driven simulator for large-scale autonomous driving research","author":"Gulino","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-31635-3_22"},{"key":"ref24","first-page":"2","author":"Hafner","year":"2019","journal-title":"Dream to control: Learning behaviors by latent imagination"},{"key":"ref25","first-page":"6","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1505"},{"key":"ref27","author":"Hu","year":"2023","journal-title":"Gaia-1: A generative world model for autonomous driving"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00757"},{"key":"ref31","author":"Jia","year":"2023","journal-title":"Adriver-i: A general world model for autonomous driving"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref33","first-page":"2","article-title":"Videopoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2024","journal-title":"ICML"},{"issue":"1","key":"ref34","article-title":"A path towards autonomous machine intelligence version 0.9. 2, 2022\u201306-27","volume":"62","author":"LeCun","year":"2022","journal-title":"Open Review"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref37","article-title":"Enhancing end-to-end autonomous driving with latent world model","author":"Li","year":"2025","journal-title":"ICLR"},{"key":"ref38","first-page":"14864","article-title":"Is ego status all you need for openloop end-to-end autonomous driving?","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li"},{"key":"ref39","first-page":"2","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems, 36"},{"key":"ref40","first-page":"7","author":"Luo","year":"2024","journal-title":"Open-magvit2: An open-source project toward democratizing auto-regressive visual generation"},{"key":"ref41","first-page":"2","author":"O\u2019Neill","year":"2023","journal-title":"Open x-embodiment: Robotic learning datasets and rt-x models"},{"key":"ref42","first-page":"4055","article-title":"Image transformer","volume-title":"International conference on machine learning","author":"Parmar"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref45","first-page":"7077","article-title":"Multimodal fusion transformer for end-to-end autonomous driving","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Prakash"},{"key":"ref46","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","first-page":"2","author":"Ruoss","year":"2024","journal-title":"Grandmaster-level chess without search"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref50","author":"Sun","year":"2024","journal-title":"Autoregressive model beats diffusion: Llama for scalable image generation"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128800"},{"key":"ref52","first-page":"2","article-title":"Chameleon Team","year":"2024","journal-title":"Chameleon: Mixed-modal early-fusion foundation models"},{"key":"ref53","first-page":"2","author":"Tian","year":"2024","journal-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction"},{"key":"ref54","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref55","first-page":"6","author":"Unterthiner","year":"2018","journal-title":"Towards accurate generative models of video: A new metric & challenges"},{"key":"ref56","first-page":"2","article-title":"Conditional image generation with pixelcnn decoders","volume":"29","author":"Van den Oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref57","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"International conference on machine learning","author":"Van Den Oord"},{"key":"ref58","first-page":"2","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref62","first-page":"2","author":"Wang","year":"2024","journal-title":"Emu3: Next-token prediction is all you need"},{"key":"ref63","first-page":"2","author":"Wang","year":"2024","journal-title":"Drivingdojo dataset: Advancing interactive and knowledge-enriched driving world model"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref65","first-page":"2","author":"Wang","year":"2024","journal-title":"Loong: Generating minute-level long videos with autoregressive language models"},{"key":"ref66","first-page":"2","author":"Wei","year":"2024","journal-title":"Occllama: An occupancy-language-action generative world model for autonomous driving"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01463"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0443"},{"key":"ref69","first-page":"2","author":"Xiang","year":"2024","journal-title":"Pandora: Towards general world model with natural language actions and video states"},{"key":"ref70","first-page":"2","author":"Yan","year":"2021","journal-title":"Videogpt: Video generation using vq-vae and transformers"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"ref72","first-page":"6","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"issue":"3","key":"ref73","first-page":"2","volume":"2","author":"Yu","year":"2022","journal-title":"Scaling autoregressive models for content-rich text-to-image generation"},{"key":"ref74","first-page":"2","author":"Yu","year":"2023","journal-title":"Language model beats diffusion-tokenizer is key to visual generation"},{"key":"ref75","article-title":"Copilot4d: Learning unsupervised world models for autonomous driving via discrete diffusion","author":"Zhang","year":"2024","journal-title":"ICLR"},{"key":"ref76","author":"Zhang","year":"2024","journal-title":"Bevworld: A multimodal world model for autonomous driving via unified bev latent space"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"}],"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\/11444276.pdf?arnumber=11444276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:50:44Z","timestamp":1777611044000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02496","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}