{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T22:06:34Z","timestamp":1788991594716,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370259","type":"print"},{"value":"9783032370266","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\/978-3-032-37026-6_25","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:10:17Z","timestamp":1788988217000},"page":"448-466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Memory-Efficient Autoregressive Video Generation via\u00a0Instance-Specific Parametric Absorption"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7195-0765","authenticated-orcid":false,"given":"Xiaomeng","family":"Fu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hayden Kwok-Hay","family":"So","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3559-8009","authenticated-orcid":false,"given":"Jiao","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangxiang","family":"Chu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1107-3873","authenticated-orcid":false,"given":"Jizhong","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"25_CR1","unstructured":"Behnam, P., Fu, Y., Zhao, R., Tsai, P.A., Yu, Z., Tumanov, A.: Rocketkv: accelerating long-context LLM inference via two-stage KV cache compression. In: International Conference on Machine Learning, pp. 3358\u20133392. PMLR (2025)"},{"key":"25_CR2","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"25_CR3","unstructured":"Chen, G., et al.: Skyreels-v2: infinite-length film generative model. arXiv preprint arXiv:2504.13074 (2025)"},{"key":"25_CR4","unstructured":"Cui, J., et al.: Self-forcing++: towards minute-scale high-quality video generation. arXiv preprint arXiv:2510.02283 (2025)"},{"key":"25_CR5","unstructured":"Dao, T.: Flashattention-2: faster attention with better parallelism and work partitioning. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"25_CR6","doi-asserted-by":"publisher","first-page":"16344","DOI":"10.52202\/068431-1189","volume":"35","author":"T Dao","year":"2022","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: Flashattention: fast and memory-efficient exact attention with io-awareness. Adv. Neural. Inf. Process. Syst. 35, 16344\u201316359 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR7","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Fu, X., Li, J.: TCFG: truncated classifier-free guidance for efficient and scalable text-to-image acceleration. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18552\u201318562 (2025)","DOI":"10.1109\/ICCV51701.2025.01724"},{"key":"25_CR9","unstructured":"Gu, X., et al.: When attention sink emerges in language models: an empirical view. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"25_CR10","unstructured":"Guo, H., et al.: Efficient autoregressive video diffusion with dummy head. arXiv preprint arXiv:2601.20499 (2026)"},{"key":"25_CR11","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":"25_CR12","doi-asserted-by":"crossref","unstructured":"Hooper, C.R.C., et al.: Squeezed attention: accelerating long context length LLM inference. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 32631\u201332652 (2025)","DOI":"10.18653\/v1\/2025.acl-long.1568"},{"key":"25_CR13","unstructured":"Huang, J., et al.: Live: long-horizon interactive video world modeling. arXiv:2602.03747 arXiv preprint (2026)"},{"key":"25_CR14","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":"25_CR15","unstructured":"Huang, Y., et al.: Live avatar: streaming real-time audio-driven avatar generation with infinite length. arXiv preprint arXiv:2512.04677 (2025)"},{"key":"25_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, pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"25_CR17","unstructured":"Li, J., Fu, X., Gao, Y., Wang, J., Wang, X., So, H.K.H.: Rethinking conditioning in diffusion models: dynamic token scheduling for efficient and aligned text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4160\u20134169 (2026)"},{"key":"25_CR18","unstructured":"Li, J., et al.: Train short, inference long: training-free horizon extension for autoregressive video generation. arXiv preprint arXiv:2602.14027 (2026)"},{"key":"25_CR19","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":"25_CR20","doi-asserted-by":"publisher","first-page":"22947","DOI":"10.52202\/079017-0722","volume":"37","author":"Y Li","year":"2024","unstructured":"Li, Y., et al.: Snapkv: LLM knows what you are looking for before generation. Adv. Neural. Inf. Process. Syst. 37, 22947\u201322970 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR21","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"25_CR22","doi-asserted-by":"publisher","first-page":"139997","DOI":"10.52202\/079017-4443","volume":"37","author":"A Liu","year":"2024","unstructured":"Liu, A., Liu, J., Pan, Z., He, Y., Haffari, G., Zhuang, B.: Minicache: Kv cache compression in depth dimension for large language models. Adv. Neural. Inf. Process. Syst. 37, 139997\u2013140031 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR23","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)"},{"key":"25_CR24","unstructured":"Liu, X., Gong, C.: Flow straight and fast: learning to generate and transfer data with rectified flow. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"25_CR25","unstructured":"Lu, Y., et al.: Reward forcing: efficient streaming video generation with rewarded distribution matching distillation. arXiv preprint arXiv:2512.04678 (2025)"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Ma, N., et al.: Sit: exploring flow and diffusion-based generative models with scalable interpolant transformers. In: European Conference on Computer Vision, pp. 23\u201340. Springer (2024)","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"25_CR27","unstructured":"Ma, X., et al.: Latte: latent diffusion transformer for video generation. arXiv preprint arXiv:2401.03048 (2024)"},{"key":"25_CR28","unstructured":"Ma, Y., et al.: Flow caching for autoregressive video generation. arXiv preprint arXiv:2602.10825 (2026)"},{"key":"25_CR29","unstructured":"Millon, E.: Krea realtime 14b: real-time video generation (2025). https:\/\/github.com\/krea-ai\/realtime-video"},{"key":"25_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":"25_CR31","unstructured":"Polyak, A., et al.: Movie gen: a cast of media foundation models. arXiv preprint arXiv:2410.13720 (2024)"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"25_CR33","unstructured":"Song, Y., Dhariwal, P.: Improved techniques for training consistency models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"25_CR34","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. In: International Conference on Machine Learning, pp. 32211\u201332252. PMLR (2023)"},{"key":"25_CR35","unstructured":"Tang, J., Zhao, Y., Zhu, K., Xiao, G., Kasikci, B., Han, S.: Quest: query-aware sparsity for efficient long-context LLM inference. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"25_CR36","unstructured":"Gao, Z., et al.: Advancing open-source world models. arXiv preprint arXiv:2601.20540 (2026)"},{"key":"25_CR37","unstructured":"Teng, H., et al.: Magi-1: autoregressive video generation at scale. arXiv preprint arXiv:2505.13211 (2025)"},{"key":"25_CR38","unstructured":"Villegas, R., et al.: Phenaki: variable length video generation from open domain textual descriptions. In: International Conference on Learning Representations (2022)"},{"key":"25_CR39","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Wang, A., et al.: Prefixkv: adaptive prefix KV cache is what vision instruction-following models need for efficient generation. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2026)","DOI":"10.52202\/085713-3159"},{"key":"25_CR41","unstructured":"Wu, H., et al.: Geometry forcing: marrying video diffusion and 3D representation for consistent world modeling. arXiv preprint arXiv:2507.07982 (2025)"},{"key":"25_CR42","unstructured":"Wu, X., Zhang, G., Xu, Z., Zhou, Y., Lu, Q., He, X.: Pack and force your memory: long-form and consistent video generation. arXiv preprint arXiv:2510.01784 (2025)"},{"key":"25_CR43","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":"25_CR44","unstructured":"Yang, S., et al.: Longlive: real-time interactive long video generation. arXiv preprint arXiv:2509.22622 (2025)"},{"key":"25_CR45","unstructured":"Yang, Z., et al.: Cogvideox: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"25_CR46","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":"25_CR47","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":"25_CR48","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":"25_CR49","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":"25_CR50","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: From slow bidirectional to fast autoregressive video diffusion models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 22963\u201322974 (2025)","DOI":"10.1109\/CVPR52734.2025.02138"},{"key":"25_CR51","unstructured":"Yu, Z., Wang, Z., Fu, Y., Shi, H., Shaikh, K., Lin, Y.C.: Unveiling and harnessing hidden attention sinks: enhancing large language models without training through attention calibration. In: International Conference on Machine Learning, pp. 57659\u201357677. PMLR (2024)"},{"key":"25_CR52","unstructured":"Zhang, J., Huang, H., Zhang, P., Wei, J., Zhu, J., Chen, J.: Sageattention2: efficient attention with thorough outlier smoothing and per-thread int4 quantization. In: International Conference on Machine Learning, pp. 75097\u201375119. PMLR (2025)"},{"key":"25_CR53","unstructured":"Zhang, J., Zhang, P., Zhu, J., Chen, J., et\u00a0al.: Sageattention: accurate 8-bit attention for plug-and-play inference acceleration. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"25_CR54","doi-asserted-by":"publisher","first-page":"34661","DOI":"10.52202\/075280-1506","volume":"36","author":"Z Zhang","year":"2023","unstructured":"Zhang, Z., et al.: H2o: heavy-hitter oracle for efficient generative inference of large language models. Adv. Neural. Inf. Process. Syst. 36, 34661\u201334710 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR55","unstructured":"Zheng, D., et al.: Vbench-2.0: advancing video generation benchmark suite for intrinsic faithfulness. arXiv preprint arXiv:2503.21755 (2025)"},{"key":"25_CR56","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\/978-3-032-37026-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:10:23Z","timestamp":1788988223000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37026-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370259","9783032370266"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37026-6_25","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":"10 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"}}]}}