{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T06:05:58Z","timestamp":1789452358831,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374899","type":"print"},{"value":"9783032374905","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\/978-3-032-37490-5_36","type":"book-chapter","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T05:44:45Z","timestamp":1789451085000},"page":"647-664","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cycle-World: Mitigating Error Accumulation in\u00a0Long-Term Video World Models via\u00a0Reverse-Prediction Cycle Consistency"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4612-2368","authenticated-orcid":false,"given":"Zihan","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1247-5931","authenticated-orcid":false,"given":"Teng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8891-6766","authenticated-orcid":false,"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8202-213X","authenticated-orcid":false,"given":"Ruiyan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1858-3358","authenticated-orcid":false,"given":"Ran","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1653-4341","authenticated-orcid":false,"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"36_CR1","unstructured":"Bansal, H., et al.: Videophy: evaluating physical commonsense for video generation. arXiv preprint arXiv:2406.03520 (2024)"},{"key":"36_CR2","unstructured":"Bansal, H., Peng, C., Bitton, Y., Goldenberg, R., Grover, A., Chang, K.W.: Videophy-2: a challenging action-centric physical commonsense evaluation in video generation. arXiv preprint arXiv:2503.06800 (2025)"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"36_CR4","unstructured":"Cai, Y., et al.: Omnivcus: feedforward subject-driven video customization with multimodal control conditions. In: Belgrave, D., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a038, pp. 115404\u2013115423. Curran Associates, Inc. (2025). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2025\/file\/a79054a9da91d73ed3cb1a9e87d7cd2d-Paper-Conference.pdf"},{"key":"36_CR5","doi-asserted-by":"publisher","first-page":"24081","DOI":"10.52202\/079017-0759","volume":"37","author":"B Chen","year":"2024","unstructured":"Chen, B., Mart\u00ed Mons\u00f3, D., Du, Y., Simchowitz, M., Tedrake, R., Sitzmann, V.: Diffusion forcing: next-token prediction meets full-sequence diffusion. Adv. Neural. Inf. Process. Syst. 37, 24081\u201324125 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR6","unstructured":"Chen, G., et al.: Skyreels-v2: infinite-length film generative model. arXiv preprint arXiv:2504.13074 (2025)"},{"key":"36_CR7","unstructured":"Chen, S., et al.: Context forcing: consistent autoregressive video generation with long context. arXiv preprint arXiv:2602.06028 (2026)"},{"key":"36_CR8","unstructured":"Chen, X., et al.: Seine: short-to-long video diffusion model for generative transition and prediction. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"36_CR9","unstructured":"Cui, J., et al.: Self-forcing++: towards minute-scale high-quality video generation. arXiv preprint arXiv:2510.02283 (2025)"},{"key":"36_CR10","unstructured":"Deng, H., et al.: Autoregressive video generation without vector quantization. arXiv preprint arXiv:2412.14169 (2024)"},{"issue":"3","key":"36_CR11","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1006\/bbrc.2000.2471","volume":"270","author":"IY Dobrosotskaya","year":"2000","unstructured":"Dobrosotskaya, I.Y., James, G.L.: Magi-1 interacts with $$\\beta $$-catenin and is associated with cell-cell adhesion structures. Biochem. Biophys. Res. Commun. 270(3), 903\u2013909 (2000)","journal-title":"Biochem. Biophys. Res. Commun."},{"key":"36_CR12","unstructured":"Gao, Y., et al.: Seedance 1.0: exploring the boundaries of video generation models. arXiv preprint arXiv:2506.09113 (2025)"},{"key":"36_CR13","unstructured":"HaCohen, Y., et al.: LTX-video: realtime video latent diffusion. arXiv preprint arXiv:2501.00103 (2024)"},{"key":"36_CR14","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":"36_CR15","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: Cogvideo: large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868 (2022)"},{"issue":"1","key":"36_CR16","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s41095-022-0307-3","volume":"10","author":"S Hou","year":"2024","unstructured":"Hou, S., et al.: A causal convolutional neural network for multi-subject motion modeling and generation. Comput. Vis. Media 10(1), 45\u201359 (2024). https:\/\/doi.org\/10.1007\/s41095-022-0307-3","journal-title":"Comput. Vis. Media"},{"key":"36_CR17","unstructured":"Hu, T., et al.: Metaworld: scaling multi-agent video world model from single-view video data (2026). https:\/\/arxiv.org\/abs\/2606.02753"},{"key":"36_CR18","unstructured":"Hu, T., et al.: Harmony: harmonizing audio and video generation through cross-task synergy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16085\u201316095 (2026)"},{"key":"36_CR19","unstructured":"Hu, T., et al.: Hunyuancustom: a multimodal-driven architecture for customized video generation (2025). https:\/\/arxiv.org\/abs\/2505.04512"},{"key":"36_CR20","unstructured":"Hu, T., et al.: Polyvivid: vivid multi-subject video generation with cross-modal interaction and enhancement. In: Belgrave, D., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a038, pp. 49394\u201349420. Curran Associates, Inc. (2025). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2025\/file\/4683beb6bab325650db13afd05d1a14a-Paper-Conference.pdf"},{"key":"36_CR21","unstructured":"Hu, T., et al.: Evolution of video generative foundations (2026). https:\/\/arxiv.org\/abs\/2604.06339"},{"key":"36_CR22","unstructured":"Hu, T., Zhang, J., Su, Z., Yi, R.: Ultragen: high-resolution video generation with hierarchical attention (2025). https:\/\/arxiv.org\/abs\/2510.18775"},{"key":"36_CR23","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 preprint arXiv:2506.08009 (2025)","DOI":"10.52202\/085713-5576"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: VBench: comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"36_CR25","unstructured":"Team HunyuanWorld: HY-world 1.5: a systematic framework for interactive world modeling with real-time latency and geometric consistency. arXiv preprint (2025)"},{"key":"36_CR26","unstructured":"Jin, Y., et al.: Pyramidal flow matching for efficient video generative modeling. arXiv preprint arXiv:2410.05954 (2024)"},{"key":"36_CR27","doi-asserted-by":"publisher","unstructured":"Karacan, L., Sar\u0131g\u00fcl, M.: Full-frame video stabilization via spatiotemporal transformers. Comput. Vis. Media 11(3), 655\u2013667 (2025). https:\/\/doi.org\/10.26599\/CVM.2025.9450416","DOI":"10.26599\/CVM.2025.9450416"},{"key":"36_CR28","unstructured":"Kondratyuk, D., et al.: Videopoet: a large language model for zero-shot video generation. arXiv preprint arXiv:2312.14125 (2023)"},{"key":"36_CR29","unstructured":"Kong, W., et al.: Hunyuanvideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"36_CR30","unstructured":"Liu, K., et al.: Javisdit++: unified modeling and optimization for joint audio-video generation. In: The Fourteenth International Conference on Learning Representations (2026)"},{"key":"36_CR31","unstructured":"Liu, K., Hu, W., Xu, J., Shan, Y., Lu, S.: Rolling forcing: autoregressive long video diffusion in real time. arXiv preprint arXiv:2509.25161 (2025)"},{"issue":"2","key":"36_CR32","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s41095-023-0342-8","volume":"10","author":"Y Liu","year":"2024","unstructured":"Liu, Y., et al.: Temporally consistent video colorization with deep feature propagation and self-regularization learning. Comput. Vis. Media 10(2), 375\u2013395 (2024). https:\/\/doi.org\/10.1007\/s41095-023-0342-8","journal-title":"Comput. Vis. Media"},{"key":"36_CR33","unstructured":"Low, C., Wang, W., Katyal, C.: OVI: twin backbone cross-modal fusion for audio-video generation (2025). https:\/\/arxiv.org\/abs\/2510.01284"},{"key":"36_CR34","unstructured":"Mao, X., et al.: Yume-1.5: a text-controlled interactive world generation model. arXiv preprint arXiv:2512.22096 (2025)"},{"key":"36_CR35","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"36_CR36","unstructured":"OpenAI: Sora (2024). https:\/\/openai.com\/sora"},{"key":"36_CR37","unstructured":"OpenAI: Sora 2 (2025). https:\/\/openai.com\/index\/sora-2\/"},{"key":"36_CR38","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":"36_CR39","unstructured":"Qiu, H., et al.: Freenoise: tuning-free longer video diffusion via noise rescheduling. arXiv preprint arXiv:2310.15169 (2023)"},{"key":"36_CR40","unstructured":"Rasul, K., Seward, C., Schuster, I., Vollgraf, R.: Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting. In: International Conference on Machine Learning, pp. 8857\u20138868. PMLR (2021)"},{"key":"36_CR41","unstructured":"Seed, B.: Seedance 2.0 (2026). https:\/\/seed.bytedance.com\/en\/seedance2_0"},{"key":"36_CR42","unstructured":"Skywork AI Matrix-Game Team: Matrix-game 3.0: Real-time and streaming interactive world model with long-horizon memory. Technical report (2026). https:\/\/github.com\/SkyworkAI\/Matrix-Game\/blob\/main\/Matrix-Game-3\/assets\/pdf\/report.pdf"},{"key":"36_CR43","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"36_CR44","unstructured":"Kuaishou Technology: Kling (2025). https:\/\/kling.kuaishou.com\/"},{"key":"36_CR45","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"36_CR46","unstructured":"Wang, D., et al.: Universe-1: unified audio-video generation via stitching of experts. arXiv preprint arXiv:2509.06155 (2025)"},{"key":"36_CR47","unstructured":"Wang, F.Y., Chen, W., Song, G., Ye, H.J., Liu, Y., Li, H.: Gen-l-video: multi-text to long video generation via temporal co-denoising. arXiv preprint arXiv:2305.18264 (2023)"},{"key":"36_CR48","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Lingen: towards high-resolution minute-length text-to-video generation with linear computational complexity. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2578\u20132588 (2025)","DOI":"10.1109\/CVPR52734.2025.00246"},{"issue":"2","key":"36_CR49","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","volume":"1","author":"RJ Williams","year":"1989","unstructured":"Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1(2), 270\u2013280 (1989)","journal-title":"Neural Comput."},{"key":"36_CR50","unstructured":"Yang, S., et al.: Longlive: real-time interactive long video generation. arXiv preprint arXiv:2509.22622 (2025)"},{"key":"36_CR51","unstructured":"Yang, Z., et al.: Cogvideox: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"36_CR52","unstructured":"Yesiltepe, H., Meral, T.H.S., Akan, A.K., Oktay, K., Yanardag, P.: Infinity-rope: action-controllable infinite video generation emerges from autoregressive self-rollout. arXiv preprint arXiv:2511.20649 (2025)"},{"key":"36_CR53","doi-asserted-by":"crossref","unstructured":"Yin, S., et al.: NUWA-XL: diffusion over diffusion for extremely long video generation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1309\u20131320 (2023)","DOI":"10.18653\/v1\/2023.acl-long.73"},{"key":"36_CR54","doi-asserted-by":"publisher","first-page":"47455","DOI":"10.52202\/079017-1505","volume":"37","author":"T Yin","year":"2024","unstructured":"Yin, T., et al.: Improved distribution matching distillation for fast image synthesis. Adv. Neural. Inf. Process. Syst. 37, 47455\u201347487 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR55","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":"36_CR56","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: From slow bidirectional to fast autoregressive video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22963\u201322974 (2025)","DOI":"10.1109\/CVPR52734.2025.02138"},{"key":"36_CR57","unstructured":"Zhang, G., et al.: Uniavgen: unified audio and video generation with asymmetric cross-modal interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1950\u20131960 (2026)"},{"key":"36_CR58","unstructured":"Zheng, D., et al.: VBench-2.0: advancing video generation benchmark suite for intrinsic faithfulness. arXiv preprint arXiv:2503.21755 (2025)"},{"key":"36_CR59","unstructured":"Zheng, Z., et al.: Open-sora: democratizing efficient video production for all. arXiv preprint arXiv:2412.20404 (2024)"},{"key":"36_CR60","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\/978-3-032-37490-5_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T05:45:07Z","timestamp":1789451107000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37490-5_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374899","9783032374905"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37490-5_36","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":"16 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"}}]}}