{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T04:00:59Z","timestamp":1785902459250,"version":"3.56.0"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":[[2026,6]]},"DOI":"10.1109\/ivworkshops71735.2026.11623987","type":"proceedings-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T19:09:51Z","timestamp":1785438591000},"page":"2198-2205","source":"Crossref","is-referenced-by-count":1,"title":["OpenViCA: Video Continuation for Automotive Driving Scenes by Streamlining and Fine-Tuning Open Source Models with Public Data"],"prefix":"10.1109","author":[{"given":"Bj\u00f6rn","family":"M\u00f6ller","sequence":"first","affiliation":[{"name":"Technische Universit\u00e4t Braunschweig","place":["Braunschweig, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyang","family":"Li","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Braunschweig","place":["Braunschweig, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malte","family":"Stelzer","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Braunschweig","place":["Braunschweig, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Graave","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Braunschweig","place":["Braunschweig, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian","family":"Bettels","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Braunschweig","place":["Braunschweig, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muaaz","family":"Ataya","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Braunschweig","place":["Braunschweig, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Fingscheidt","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Braunschweig","place":["Braunschweig, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref2","article-title":"LLaMA: Open and Efficient Foundation Language Models","author":"Touvron","year":"2023"},{"key":"ref3","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023"},{"key":"ref4","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume-title":"Proc. of NeurIPS","volume":"33","author":"Ho"},{"key":"ref5","article-title":"GAIA-1: A Generative World Model for Autonomous Driving","author":"Hu","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2173"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01233-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01233-4_1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref10","article-title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","author":"Russell","year":"2025"},{"key":"ref11","article-title":"World Model on Million-Length Video And Language With Blockwise RingAttention","author":"Liu","year":"2024"},{"key":"ref12","first-page":"1","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"Proc. of ICLR","author":"Hu"},{"key":"ref13","article-title":"aMUSEd: An Open MUSE Reproduction","author":"Patil","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"ref16","first-page":"1","article-title":"Adversarial Autoencoders","volume-title":"Proc. of ICLR Workshops","author":"Makhzani"},{"key":"ref17","first-page":"1","article-title":"Auto-Encoding Variational Bayes","volume-title":"Proc. of ICLR","author":"Kingma"},{"key":"ref18","first-page":"6309","article-title":"Neural Discrete Representation Learning","volume-title":"Proc. of NIPS","volume":"30","author":"van den Oord"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3398357"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1182"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"ref23","article-title":"VaViM and VaVAM: Autonomous Driving through Video Generative Modeling","author":"Bartoccioni","year":"2025"},{"key":"ref24","article-title":"DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT","author":"Hu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref27","article-title":"ADriver-I: A General World Model for Autonomous Driving","author":"Jia","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2906"},{"key":"ref29","article-title":"GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control","author":"Hassan","year":"2024"},{"key":"ref30","article-title":"Loong: Generating Minute-level Long Videos with Autoregressive Language Models","author":"Wang","year":"2025"},{"key":"ref31","first-page":"1","article-title":"Generating Videos with Scene Dynamics","volume-title":"Proc. of NIPS","volume":"29","author":"Vondrick"},{"key":"ref32","article-title":"VideoGPT: Video Generation using VQ-VAE and Transformers","author":"Yan","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref34","first-page":"1","article-title":"Generative Adversarial Nets","volume-title":"Proc. of NIPS","volume":"27","author":"Goodfellow"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref37","volume-title":"Digital Image Processing","author":"Gonzales","year":"2008"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref39","first-page":"1","article-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref41","volume-title":"Data Compression: The Complete Reference","author":"Salomon","year":"2004"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref45","first-page":"6626","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","volume-title":"Proc. of NIPS","volume":"30","author":"Heusel"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"ref47","first-page":"1","article-title":"FVD: A New Metric for Video Generation","volume-title":"Proc. of ICLR Workshops","author":"Unterthiner"},{"key":"ref48","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Paszke","year":"2019"},{"key":"ref49","article-title":"JAX: Composable Transformations of Python+NumPy Programs","author":"Bradbury","year":"2018"}],"event":{"name":"2026 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)","location":"Ann Arbor, MI, USA","start":{"date-parts":[[2026,6,22]]},"end":{"date-parts":[[2026,6,22]]}},"container-title":["2026 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11623814\/11623822\/11623987.pdf?arnumber=11623987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T04:49:33Z","timestamp":1785473373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11623987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/ivworkshops71735.2026.11623987","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}