{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T20:36:19Z","timestamp":1791059779195,"version":"4.1.0"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370099","type":"print"},{"value":"9783032370105","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37010-5_8","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:55:21Z","timestamp":1790232921000},"page":"134-151","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CausalDrive: Real-Time Causal World Models for\u00a0Autonomous Driving"],"prefix":"10.1007","author":[{"given":"Tianyi","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dubing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meizhi","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingying","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingfei","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hangjun","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-zhong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"8_CR1","unstructured":"Agarwal, N., et\u00a0al.: Cosmos world foundation model platform for physical AI. arXiv preprint arXiv:2501.03575 (2025)"},{"key":"8_CR2","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv:2311.15127 arXiv preprint (2023)"},{"key":"8_CR3","unstructured":"Caesar, H., et al.: nuplan: a closed-loop ml-based planning benchmark for autonomous vehicles. arXiv:2106.11810 arXiv preprint (2021)"},{"key":"8_CR4","unstructured":"Chen, S., et al.: Vadv2: end-to-end vectorized autonomous driving via probabilistic planning. arXiv:2402.13243 arXiv preprint (2024)"},{"key":"8_CR5","unstructured":"Chi, H., et al.: Driver-WM: a driver-centric traffic-conditioned latent world model for in-cabin dynamics rollout. arXiv:2605.05092 arXiv preprint (2026)"},{"key":"8_CR6","doi-asserted-by":"publisher","first-page":"28706","DOI":"10.52202\/079017-0902","volume":"37","author":"D Dauner","year":"2024","unstructured":"Dauner, D., et al.: Navsim: data-driven non-reactive autonomous vehicle simulation and benchmarking. Adv. Neural. Inf. Process. Syst. 37, 28706\u201328719 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR7","unstructured":"Deng, T., et al.: Gaussiandwm: 3d gaussian driving world model for unified scene understanding and multi-modal generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10656\u201310667 (2026)"},{"key":"8_CR8","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: Carla: an open urban driving simulator. In: Conference on Robot Learning, pp. 1\u201316. PMLR (2017)"},{"key":"8_CR9","unstructured":"Gao, R., Chen, K., Xiao, B., Hong, L., Li, Z., Xu, Q.: Magicdrivedit: High-resolution long video generation for autonomous driving with adaptive control. arXiv:2411.13807 arXiv preprint (2024)"},{"key":"8_CR10","unstructured":"Gao, R., et al.: Magicdrive: street view generation with diverse 3d geometry control. arXiv:2310.02601 arXiv preprint (2023)"},{"key":"8_CR11","doi-asserted-by":"publisher","first-page":"91560","DOI":"10.52202\/079017-2906","volume":"37","author":"S Gao","year":"2024","unstructured":"Gao, S., et al.: Vista: a generalizable driving world model with high fidelity and versatile controllability. Adv. Neural. Inf. Process. Syst. 37, 91560\u201391596 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Hassan, M., et al.: Gem: a generalizable ego-vision multimodal world model for fine-grained ego-motion, object dynamics, and scene composition control. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22404\u201322415 (2025)","DOI":"10.1109\/CVPR52734.2025.02087"},{"key":"8_CR13","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR14","unstructured":"Hu, A., et al.: Gaia-1: a generative world model for autonomous driving. arXiv:2309.17080 arXiv preprint (2023)"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Hu, Y., et\u00a0al.: Planning-oriented autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17853\u201317862 (2023)","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, Z., He, G., Zhou, M., Shechtman, E.: Self forcing: bridging the train-test gap in autoregressive video diffusion. arXiv:2506.08009 arXiv preprint (2025)","DOI":"10.52202\/085713-5576"},{"key":"8_CR17","doi-asserted-by":"publisher","first-page":"819","DOI":"10.52202\/079017-0025","volume":"37","author":"X Jia","year":"2024","unstructured":"Jia, X., Yang, Z., Li, Q., Zhang, Z., Yan, J.: Bench2drive: towards multi-ability benchmarking of closed-loop end-to-end autonomous driving. Adv. Neural. Inf. Process. Syst. 37, 819\u2013844 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, B., et al.: Vad: vectorized scene representation for efficient autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8340\u20138350 (2023)","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Li, B., et\u00a0al.: Uniscene: unified occupancy-centric driving scene generation. arXiv preprint arXiv:2412.05435 (2024)","DOI":"10.1109\/CVPR52734.2025.01118"},{"issue":"3","key":"8_CR20","doi-asserted-by":"publisher","first-page":"3461","DOI":"10.1109\/TPAMI.2022.3190471","volume":"45","author":"Q Li","year":"2022","unstructured":"Li, Q., Peng, Z., Feng, L., Zhang, Q., Xue, Z., Zhou, B.: Metadrive: composing diverse driving scenarios for generalizable reinforcement learning. IEEE Trans. Patt. Anal. Mach. Intell. 45(3), 3461\u20133475 (2022)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"8_CR21","unstructured":"Li, R., et al.: Amap: distilling future priors for ahead-aware online HD map construction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24906\u201324917 (2026)"},{"key":"8_CR22","unstructured":"Li, Y., et\u00a0al.: Recogdrive: a reinforced cognitive framework for end-to-end autonomous driving. arXiv preprint arXiv:2506.08052 (2025)"},{"key":"8_CR23","unstructured":"Liang, A., et\u00a0al.: Worldlens: full-spectrum evaluations of driving world models in real world. arXiv preprint arXiv:2512.10958 (2025)"},{"key":"8_CR24","doi-asserted-by":"publisher","first-page":"10421","DOI":"10.52202\/068431-0757","volume":"35","author":"T Liang","year":"2022","unstructured":"Liang, T., et al.: Bevfusion: a simple and robust lidar-camera fusion framework. Adv. Neural. Inf. Process. Syst. 35, 10421\u201310434 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Liao, B., et\u00a0al.: Diffusiondrive: truncated diffusion model for end-to-end autonomous driving. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12037\u201312047 (2025)","DOI":"10.1109\/CVPR52734.2025.01124"},{"key":"8_CR26","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv:2210.02747 arXiv preprint (2022)"},{"key":"8_CR27","unstructured":"Lu, G., et al.: VLA-RL: towards masterful and general robotic manipulation with scalable reinforcement learning. arXiv:2505.18719 arXiv preprint (2025)"},{"key":"8_CR28","unstructured":"Mai, J., et al.: Neural predictor-corrector: solving homotopy problems with reinforcement learning. arXiv preprint arXiv:2602.03086 (2026)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Mousakhan, A., Mittal, S., Galesso, S., Farid, K., Brox, T.: Orbis: overcoming challenges of long-horizon prediction in driving world models. arXiv:2507.13162 arXiv preprint (2025)","DOI":"10.52202\/085713-0167"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Shang, S., Chen, Y., Wang, Y., Li, Y., Zhang, Z.: Drivedpo: policy learning via safety DPO for end-to-end autonomous driving. arXiv:2509.17940 arXiv preprint (2025)","DOI":"10.52202\/085713-2724"},{"key":"8_CR32","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models (2023)"},{"key":"8_CR33","unstructured":"Tian, H., et\u00a0al.: Simscale: learning to drive via real-world simulation at scale. arXiv preprint arXiv:2511.23369 (2025)"},{"key":"8_CR34","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, Z., Huang, G., Chen, X., Zhu, J., Lu, J.: Drivedreamer: towards real-world-drive world models for autonomous driving. In: European Conference on Computer Vision, pp. 55\u201372. Springer (2024)","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Y., He, J., Fan, L., Li, H., Chen, Y., Zhang, Z.: Driving into the future: multiview visual forecasting and planning with world model for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14749\u201314759 (2024)","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Wen, Y., et al.: Panacea: panoramic and controllable video generation for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6902\u20136912 (2024)","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: Turboreg: turboclique for robust and efficient point cloud registration. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 26371\u201326381 (2025)","DOI":"10.1109\/ICCV51701.2025.02447"},{"key":"8_CR39","unstructured":"Yan, T., et al.: Ad-r1: closed-loop reinforcement learning for end-to-end autonomous driving with impartial world models. arXiv:2511.20325 arXiv preprint (2025)"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Yan, T., et al.: Drivingsphere: building a high-fidelity 4d world for closed-loop simulation. arXiv:2411.11252 arXiv preprint (2024)","DOI":"10.1109\/CVPR52734.2025.02564"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Yan, T., Yin, J., Lang, X., Yang, R., Xu, C.Z., Shen, J.: Olidm: object-aware lidar diffusion models for autonomous driving. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a039, pp. 9121\u20139129 (2025)","DOI":"10.1609\/aaai.v39i9.32987"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Resim: reliable world simulation for autonomous driving. arXiv preprint arXiv:2506.09981 (2025)","DOI":"10.52202\/085713-5591"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Generalized predictive model for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14662\u201314672 (2024)","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: Drivearena: a closed-loop generative simulation platform for autonomous driving. arXiv:2408.00415 arXiv preprint (2024)","DOI":"10.1109\/ICCV51701.2025.02500"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: One-step diffusion with distribution matching distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6613\u20136623 (2024)","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, G., et al.: Drivedreamer-2: LLM-enhanced world models for diverse driving video generation. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a039, pp. 10412\u201310420 (2025)","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"8_CR47","unstructured":"Zhao, Z., et al.: Advances in global solvers for 3d vision. arXiv:2602.14662 arXiv preprint (2026)"},{"key":"8_CR48","unstructured":"Zhu, H., Zhao, M., He, G., Su, H., Li, C., Zhu, J.: Causal forcing: autoregressive diffusion distillation done right for high-quality real-time interactive video generation. arXiv preprint arXiv:2602.02214 (2026)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37010-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:55:32Z","timestamp":1790232932000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37010-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370099","9783032370105"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37010-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}