{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:47:37Z","timestamp":1781621257001,"version":"3.54.5"},"reference-count":71,"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\/iccv51701.2025.02527","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27220-27230","source":"Crossref","is-referenced-by-count":3,"title":["Epona: Autoregressive Diffusion World Model for Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Kaiwen","family":"Zhang","sequence":"first","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Tang","sequence":"additional","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaotao","family":"Hu","sequence":"additional","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingang","family":"Pan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyang","family":"Guo","sequence":"additional","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwei","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shenzhen Gruaduate School, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Xiao","family":"Long","sequence":"additional","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Cao","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Yin","sequence":"additional","affiliation":[{"name":"Horizon Robotics"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref2","volume-title":"Building normalizing flows with stochastic interpolants","author":"Albergo","year":"2023"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","article-title":"nuplan: A closed-loop ml-based planning benchmark for autonomous vehicles","author":"Caesar","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0759"},{"key":"ref9","article-title":"Deep compression autoencoder for efficient high-resolution diffusion models","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"Vadv2: End-to-end vectorized autonomous driving via probabilistic planning","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref11","article-title":"Drivinggpt: Unifying driving world modeling and planning with multi-modal autoregressive transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref12","article-title":"Navsim: Data-driven nonreactive autonomous vehicle simulation and benchmarking","author":"Dauner","year":"2024","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3746449"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01268"},{"key":"ref15","volume-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref16","article-title":"Magicdrivedit: High-resolution long video generation for autonomous driving with adaptive control","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","article-title":"MagicDrive: Street view generation with diverse 3d geometry control","author":"Gao","year":"2024","journal-title":"ICLR"},{"key":"ref18","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"Dome: Taming diffusion model into high-fidelity controllable occupancy world model","author":"Gu","year":"2024","journal-title":"ArXiv, abs\/2410.10429"},{"key":"ref20","volume-title":"Infinitydrive: Breaking time limits in driving world models","author":"Guo","year":"2024"},{"key":"ref21","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref22","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":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems","author":"Ho","year":"2020"},{"key":"ref24","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref26","article-title":"Drivingworld: Constructingworld model for autonomous driving via video gpt","author":"Hu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","volume-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Hunyuan","year":"2024"},{"key":"ref28","volume-title":"Adriver-i: A general world model for autonomous driving","author":"Jia","year":"2023"},{"key":"ref29","article-title":"Mgvq: Could vq-vae beat vae? a generalizable tokenizer with multigroup quantization","author":"Jia","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref31","article-title":"Fifo-diffusion: Generating infinite videos from text without training","author":"Kim","year":"2024","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"ref33","article-title":"Black Forest Labs","volume-title":"Flux","year":"2024"},{"issue":"1","key":"ref34","first-page":"1","volume":"62","author":"LeCun","year":"2022","journal-title":"A path towards autonomous machine intelligence version 0.9. 2, 2022\u201306\u221227. Open Review"},{"key":"ref35","volume-title":"Enhancing end-to-end autonomous driving with latent world model","author":"Li"},{"key":"ref36","volume-title":"Flow matching for generative modeling","author":"Lipman","year":"2023"},{"key":"ref37","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_19"},{"key":"ref39","volume-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024"},{"key":"ref40","article-title":"Janusflow: Harmonizing autoregression and rectified flow for unified multimodal understanding and generation","author":"Ma","year":"2024","journal-title":"ArXiv, abs\/2411.07975"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref43","volume-title":"Freenoise: Tuning-free longer video diffusion via noise rescheduling","author":"Qiu","year":"2023"},{"key":"ref44","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI blog"},{"issue":"8","key":"ref45","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref46","article-title":"Einops: Clear and reliable tensor manipulations with einstein-like notation","volume-title":"International Conference on Learning Representations","author":"Rogozhnikov","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3009957"},{"key":"ref49","volume-title":"History-guided video diffusion","author":"Song","year":"2025"},{"key":"ref50","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref52","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref53","volume-title":"Diffusion models are real-time game engines","author":"Valevski","year":"2024"},{"key":"ref54","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems. Curran Associates Inc."},{"key":"ref55","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref56","volume-title":"Phenaki: Variable length video generation from open domain textual description","author":"Villegas","year":"2022"},{"key":"ref57","article-title":"Gen-l-video: Multi-text to long video generation via temporal co-denoising","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_19"},{"key":"ref59","article-title":"Drivedreamer: Towards real-worlddriven world models for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref61","volume-title":"Loong: Generating minute-level long videos with autoregressive language models","author":"Wang","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01463"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00642"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00157"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.73"},{"key":"ref67","article-title":"Ang Jr au2","author":"Yuan","year":"2024","journal-title":"Drama: An efficient end-to-end motion planner for autonomous driving with mamba"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_6"},{"key":"ref70","article-title":"Doe-1: Closed-loop autonomous driving with large world model","author":"Zheng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref71","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","volume":"abs\/2408.11039","author":"Zhou","year":"2024","journal-title":"ArXiv"}],"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\/11445740.pdf?arnumber=11445740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:42Z","timestamp":1777529742000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02527","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}