{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:02:39Z","timestamp":1790276559197,"version":"4.1.0"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369833","type":"print"},{"value":"9783032369840","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\/978-3-032-36984-0_22","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:56:24Z","timestamp":1790276184000},"page":"399-416","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Anchor Forcing: Anchor Memory and\u00a0Tri-Region RoPE for\u00a0Interactive Streaming Video Diffusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0622-1275","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5157-7995","authenticated-orcid":false,"given":"Tianyi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9885-0028","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8954-0873","authenticated-orcid":false,"given":"Jinwei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4494-193X","authenticated-orcid":false,"given":"Boxi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9107-2354","authenticated-orcid":false,"given":"Xiaofei","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9817-4065","authenticated-orcid":false,"given":"Deng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7817-0665","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1786-4943","authenticated-orcid":false,"given":"Peng-Tao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"22_CR1","unstructured":"Cai, S., et\u00a0al.: Mixture of contexts for long video generation. arXiv preprint arXiv:2508.21058 (2025)"},{"key":"22_CR2","doi-asserted-by":"publisher","first-page":"24081","DOI":"10.52202\/079017-0759","volume":"37","author":"B Chen","year":"2024","unstructured":"Chen, B., et al.: 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":"22_CR3","unstructured":"Chen, G., et\u00a0al.: Skyreels-v2: Infinite-length film generative model. arXiv preprint arXiv:2504.13074 (2025)"},{"key":"22_CR4","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":"22_CR5","unstructured":"Cui, J., et al.: Lol: Longer than longer, scaling video generation to hour. arXiv preprint arXiv:2601.16914 (2026)"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Dalal, K., et al.: One-minute video generation with test-time training. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17702\u201317711 (2025)","DOI":"10.1109\/CVPR52734.2025.01649"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Feng, R., et al.: The matrix: Infinite-horizon world generation with real-time moving control. arXiv preprint arXiv:2412.03568 (2024)","DOI":"10.52202\/085713-2920"},{"key":"22_CR8","unstructured":"Gao, J., et al.: Longvie: Multimodal-guided controllable ultra-long video generation. arXiv preprint arXiv:2508.03694 (2025)"},{"key":"22_CR9","unstructured":"Gu, Y., Mao, W., Shou, M.Z.: Long-context autoregressive video modeling with next-frame prediction. arXiv preprint arXiv:2503.19325 (2025)"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Guo, Y., et al.: Long context tuning for video generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17281\u201317291 (2025)","DOI":"10.1109\/ICCV51701.2025.01605"},{"key":"22_CR11","unstructured":"HaCohen, Y., et al.: Ltx-video: Realtime video latent diffusion. arXiv preprint arXiv:2501.00103 (2024)"},{"key":"22_CR12","unstructured":"He, Y., Yang, T., Zhang, Y., Shan, Y., Chen, Q.: Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221 (2022)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Henschel, R., et al.: Streamingt2v: Consistent, dynamic, and extendable long video generation from text. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2568\u20132577 (2025)","DOI":"10.1109\/CVPR52734.2025.00245"},{"issue":"2","key":"22_CR14","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W., et al.: Lora: Low-rank adaptation of large language models. ICLR 1(2), 3 (2022)","journal-title":"ICLR"},{"key":"22_CR15","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":"22_CR16","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":"22_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633890","author":"Z Huang","year":"2025","unstructured":"Huang, Z., et al.: VBench++: Comprehensive and versatile benchmark suite for video generative models. IEEE Trans. Pattern Anal. Mach. Intell. (2025). https:\/\/doi.org\/10.1109\/TPAMI.2025.3633890","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR18","unstructured":"Ji, S., Chen, X., Yang, S., Tao, X., Wan, P., Zhao, H.: Memflow: Flowing adaptive memory for consistent and efficient long video narratives. arXiv preprint arXiv:2512.14699 (2025)"},{"key":"22_CR19","unstructured":"Jin, Y., et al.: Pyramidal flow matching for efficient video generative modeling. arXiv preprint arXiv:2410.05954 (2024)"},{"key":"22_CR20","doi-asserted-by":"publisher","first-page":"89834","DOI":"10.52202\/079017-2853","volume":"37","author":"J Kim","year":"2024","unstructured":"Kim, J., Kang, J., Choi, J., Han, B.: Fifo-diffusion: Generating infinite videos from text without training. Adv. Neural. Inf. Process. Syst. 37, 89834\u201389868 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR21","unstructured":"Li, G., et al.: Magicworld: Interactive geometry-driven video world exploration. arXiv preprint arXiv:2511.18886 (2025)"},{"key":"22_CR22","unstructured":"Li, J., et al.: Train short, inference long: Training-free horizon extension for autoregressive video generation. arXiv preprint arXiv:2602.14027 (2026)"},{"key":"22_CR23","unstructured":"Li, W., Pan, W., Luan, P.C., Gao, Y., Alahi, A.: Stable video infinity: Infinite-length video generation with error recycling. arXiv preprint arXiv:2510.09212 (2025)"},{"key":"22_CR24","doi-asserted-by":"publisher","first-page":"131434","DOI":"10.52202\/079017-4177","volume":"37","author":"Y Lu","year":"2024","unstructured":"Lu, Y., Liang, Y., Zhu, L., Yang, Y.: Freelong: Training-free long video generation with spectralblend temporal attention. Adv. Neural. Inf. Process. Syst. 37, 131434\u2013131455 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Lu, Y., Yang, Y.: Freelong++: Training-free long video generation via multi-band spectralfusion. arXiv preprint arXiv:2507.00162 (2025)","DOI":"10.52202\/079017-4177"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Mao, X., et al.: Packforcing: Short video training suffices for long video sampling and long context inference. arXiv preprint arXiv:2603.25730 (2026)","DOI":"10.1007\/978-3-032-37464-6_31"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Po, R., et al.: Long-context state-space video world models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8733\u20138744 (2025)","DOI":"10.1109\/ICCV51701.2025.00817"},{"key":"22_CR28","unstructured":"Qiu, H., et al.: Freenoise: Tuning-free longer video diffusion via noise rescheduling. arXiv preprint arXiv:2310.15169 (2023)"},{"key":"22_CR29","unstructured":"Song, K., Chen, B., Simchowitz, M., Du, Y., Tedrake, R., Sitzmann, V.: History-guided video diffusion. arXiv preprint arXiv:2502.06764 (2025)"},{"key":"22_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: Enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Tan, J., Yu, H., Huang, J., Xiao, J., Zhao, F.: Freepca: Integrating consistency information across long-short frames in training-free long video generation via principal component analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27979\u201327988 (2025)","DOI":"10.1109\/CVPR52734.2025.02605"},{"key":"22_CR32","unstructured":"Teng, H., et\u00a0al.: Magi-1: Autoregressive video generation at scale. arXiv preprint arXiv:2505.13211 (2025)"},{"key":"22_CR33","unstructured":"Tian, J., Song, C., Cheng, W., Zhang, C.: Free-lunch long video generation via layer-adaptive ood correction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1973\u20131982 (2026)"},{"key":"22_CR34","unstructured":"Villegas, R., et al.: Phenaki: Variable length video generation from open domain textual description. arXiv preprint arXiv:2210.02399 (2022)"},{"key":"22_CR35","unstructured":"Wan, T., et\u00a0al.: Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Wang, W., Yang, Y.: Vidprom: A million-scale real prompt-gallery dataset for text-to-video diffusion models. In: The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2024). https:\/\/openreview.net\/forum?id=pYNl76onJL","DOI":"10.52202\/079017-2096"},{"issue":"5","key":"22_CR37","doi-asserted-by":"publisher","first-page":"3059","DOI":"10.1007\/s11263-024-02295-1","volume":"133","author":"Y Wang","year":"2025","unstructured":"Wang, Y., et al.: Lavie: High-quality video generation with cascaded latent diffusion models. Int. J. Comput. Vision 133(5), 3059\u20133078 (2025)","journal-title":"Int. J. Comput. Vision"},{"key":"22_CR38","unstructured":"Wang, Y., et al.: Internvideo: General video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191 (2022)"},{"key":"22_CR39","unstructured":"Xiang, X., et al.: Pathwise test-time correction for autoregressive long video generation. arXiv preprint arXiv:2602.05871 (2026)"},{"key":"22_CR40","unstructured":"Xiao, G., Tian, Y., Chen, B., Han, S., Lewis, M.: Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453 (2023)"},{"key":"22_CR41","unstructured":"Yang, S., et al.: Longlive: Real-time interactive long video generation. arXiv preprint arXiv:2509.22622 (2025)"},{"key":"22_CR42","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":"22_CR43","unstructured":"Yi, J., Jang, W., Cho, P.H., Nam, J., Yoon, H., Kim, S.: Deep forcing: Training-free long video generation with deep sink and participative compression,. arXiv preprint arXiv:2512.05081 (2025)"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Yin, S., et\u00a0al.: 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":"22_CR45","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: Improved distribution matching distillation for fast image synthesis. NeurIPS (2024)","DOI":"10.52202\/079017-1505"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: One-step diffusion with distribution matching distillation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: From slow bidirectional to fast autoregressive video diffusion models. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02138"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: Context as memory: Scene-consistent interactive long video generation with memory retrieval. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201311 (2025)","DOI":"10.1145\/3757377.3763833"},{"key":"22_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, L., Cai, S., Li, M., Wetzstein, G., Agrawala, M.: Frame context packing and drift prevention in next-frame-prediction video diffusion models. arXiv preprint arXiv:2504.12626 (2025)","DOI":"10.52202\/085713-1024"},{"key":"22_CR50","unstructured":"Zhao, M., He, G., Chen, Y., Zhu, H., Li, C., Zhu, J.: Riflex: A free lunch for length extrapolation in video diffusion transformers. arXiv preprint arXiv:2502.15894 (2025)"}],"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\/978-3-032-36984-0_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:56:34Z","timestamp":1790276194000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36984-0_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369833","9783032369840"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36984-0_22","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"}}]}}