{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:06:14Z","timestamp":1788937574715,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373588","type":"print"},{"value":"9783032373595","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\/978-3-032-37359-5_10","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:06:49Z","timestamp":1788934009000},"page":"167-185","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SVG-EAR: Parameter-Free Linear Compensation for\u00a0Sparse Video Generation via\u00a0Error-aware Routing"],"prefix":"10.1007","author":[{"given":"Xuanyi","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuyang","family":"Mang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haocheng","family":"Xi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jintao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanzhi","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph E.","family":"Gonzalez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kurt","family":"Keutzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ion","family":"Stoica","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alvin","family":"Cheung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"10_CR1","unstructured":"Agarwal, K., et al.: Monarchrt: efficient attention for real-time video generation. arXiv preprint arXiv:2602.12271 (2026)"},{"key":"10_CR2","unstructured":"Bruce, J., et\u00a0al.: Genie: generative interactive environments. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"10_CR3","unstructured":"Bu, J., et al.: Dicache: let diffusion model determine its own cache. arXiv preprint arXiv:2508.17356 (2025)"},{"key":"10_CR4","unstructured":"Cai, S., et\u00a0al.: Mixture of contexts for long video generation. arXiv preprint arXiv:2508.21058 (2025)"},{"key":"10_CR5","unstructured":"Chen, A., et al.: Rainfusion2. 0: temporal-spatial awareness and hardware-efficient block-wise sparse attention. arXiv preprint arXiv:2512.24086 (2025)"},{"key":"10_CR6","unstructured":"Chen, J., et\u00a0al.: Sana-video: efficient video generation with block linear diffusion transformer. arXiv preprint arXiv:2509.24695 (2025)"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Chen, R., Mills, K., Jiang, L., Gao, C., Niu, D.: Re-ttention: ultra sparse visual generation via attention statistical reshape. In: Belgrave, D., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a038, pp. 58029\u201358055. Curran Associates, Inc. (2025)","DOI":"10.52202\/085713-1945"},{"key":"10_CR8","unstructured":"Chen, S., et al.: Context forcing: consistent autoregressive video generation with long context. arXiv preprint arXiv:2602.06028 (2026)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Chu, H., Wu, W., Feng, G., Zhang, Y.: Omnicache: a trajectory-oriented global perspective on training-free cache reuse for diffusion transformer models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16302\u201316312 (2025)","DOI":"10.1109\/ICCV51701.2025.01513"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Chu, X., Li, R., Wang, Y.: Usp: unified self-supervised pretraining for image generation and understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18475\u201318486 (2025)","DOI":"10.1109\/ICCV51701.2025.01717"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Fang, J., Pan, J., Li, A., Sun, X., Wang, J.: Pipefusion: patch-level pipeline parallelism for diffusion transformers inference. arXiv preprint arXiv:2405.14430 (2024)","DOI":"10.52202\/085713-3289"},{"key":"10_CR12","unstructured":"Fang, J., Pan, J., Sun, X., Li, A., Wang, J.: xdit: an inference engine for diffusion transformers (dits) with massive parallelism. arXiv preprint arXiv:2411.01738 (2024)"},{"key":"10_CR13","unstructured":"Fang, T., et al.: Salad: achieve high-sparsity attention via efficient linear attention tuning for video diffusion transformer. arXiv preprint arXiv:2601.16515 (2026)"},{"key":"10_CR14","unstructured":"Feng, T., et\u00a0al.: Streamdiffusionv2: a streaming system for dynamic and interactive video generation. arXiv preprint arXiv:2511.07399 (2025)"},{"key":"10_CR15","unstructured":"Gao, J., et al.: Longvie 2: multimodal controllable ultra-long video world model. arXiv preprint arXiv:2512.13604 (2025)"},{"key":"10_CR16","unstructured":"Gao, Y., Huang, J., Sun, X., Jie, Z., Zhong, Y., Ma, L.: Matten: video generation with mamba-attention. arXiv preprint arXiv:2405.03025 (2024)"},{"key":"10_CR17","unstructured":"Huang, J., et al.: M4v: multi-modal mamba for text-to-video generation. arXiv preprint arXiv:2506.10915 (2025)"},{"key":"10_CR18","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":"10_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., et\u00a0al.: 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":"10_CR20","unstructured":"HunyuanWorld, T.: Hunyuanworld 1.0: Generating immersive, explorable, and interactive 3d worlds from words or pixels. arXiv preprint (2025)"},{"key":"10_CR21","unstructured":"HunyuanWorld, T.: Hy-world 1.5: A systematic framework for interactive world modeling with real-time latency and geometric consistency. arXiv preprint (2025)"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Jacobs, S.A., et al.: Deepspeed ulysses: system optimizations for enabling training of extreme long sequence transformer models. arXiv preprint arXiv:2309.14509 (2023)","DOI":"10.1109\/IPDPSW63119.2024.00208"},{"key":"10_CR23","doi-asserted-by":"publisher","unstructured":"Jiang, H., et al.: Minference 1.0: accelerating pre-filling for long-context llms via dynamic sparse attention. In: Globerson, A., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a037, pp. 52481\u201352515. Curran Associates, Inc. (2024). https:\/\/doi.org\/10.52202\/079017-1663","DOI":"10.52202\/079017-1663"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Kahatapitiya, K., et al.: Adaptive caching for faster video generation with diffusion transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15240\u201315252 (2025)","DOI":"10.1109\/ICCV51701.2025.01414"},{"key":"10_CR25","unstructured":"Kong, W., et\u00a0al.: Hunyuanvideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"10_CR26","unstructured":"Li, H., et al.: Pisa: piecewise sparse attention is wiser for efficient diffusion transformers. arXiv preprint arXiv:2602.01077 (2026)"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Distrifusion: distributed parallel inference for high-resolution diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7183\u20137193 (2024)","DOI":"10.1109\/CVPR52733.2024.00686"},{"key":"10_CR28","unstructured":"Li, M., et al.: Svdquant: absorbing outliers by low-rank components for 4-bit diffusion models. arXiv preprint arXiv:2411.05007 (2024)"},{"key":"10_CR29","unstructured":"Li, X., Gu, Y., Lin, X., Wang, W., Zhuang, B.: Psa: pyramid sparse attention for efficient video understanding and generation. arXiv preprint arXiv:2512.04025 (2025)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Radial attention: $$o(n\\log n)$$ sparse attention with energy decay for long video generation (2025)","DOI":"10.52202\/085713-0568"},{"key":"10_CR31","unstructured":"Li, Z., et al.: Dvd-quant: data-free video diffusion transformers quantization. arXiv preprint arXiv:2505.18663 (2025)"},{"key":"10_CR32","unstructured":"Liang, C., et al.: Vmonarch: efficient video diffusion transformers with structured attention. arXiv preprint arXiv:2601.22275 (2026)"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: Timestep embedding tells: it\u2019s time to cache for video diffusion model. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 7353\u20137363 (2025)","DOI":"10.1109\/CVPR52734.2025.00689"},{"key":"10_CR34","unstructured":"Liu, H., Zaharia, M., Abbeel, P.: Ring attention with blockwise transformers for near-infinite context. arXiv preprint arXiv:2310.01889 (2023)"},{"key":"10_CR35","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":"10_CR36","unstructured":"Liu, Y., Hu, Y., Zhang, Z., Jiang, K., Yuan, K.: Mixture of distributions matters: dynamic sparse attention for efficient video diffusion transformers. arXiv preprint arXiv:2601.11641 (2026)"},{"key":"10_CR37","unstructured":"Lu, C., Song, Y.: Simplifying, stabilizing and scaling continuous-time consistency models (2025)"},{"key":"10_CR38","unstructured":"Lv, C., Shi, Y., Huang, Y., Gong, R., Ren, S., Wang, W.: Light forcing: accelerating autoregressive video diffusion via sparse attention. arXiv preprint arXiv:2602.04789 (2026)"},{"key":"10_CR39","unstructured":"Lv, Z., et al.: Fastercache: training-free video diffusion model acceleration with high quality. arXiv preprint arXiv:2410.19355 (2024)"},{"key":"10_CR40","doi-asserted-by":"publisher","first-page":"133282","DOI":"10.52202\/079017-4236","volume":"37","author":"X Ma","year":"2024","unstructured":"Ma, X., Fang, G., Bi Mi, M., Wang, X.: Learning-to-cache: accelerating diffusion transformer via layer caching. Adv. Neural. Inf. Process. Syst. 37, 133282\u2013133304 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Ma, X., Fang, G., Wang, X.: Deepcache: accelerating diffusion models for free. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15762\u201315772 (2024)","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"Ma, Z., Wei, L., Wang, F., Zhang, S., Tian, Q.: Magcache: fast video generation with magnitude-aware cache. arXiv preprint arXiv:2506.09045 (2025)","DOI":"10.52202\/085713-1153"},{"key":"10_CR43","doi-asserted-by":"crossref","unstructured":"Sun, W., et al.: Vorta: efficient video diffusion via routing sparse attention. arXiv preprint arXiv:2505.18809 (2025)","DOI":"10.52202\/085713-0268"},{"key":"10_CR44","unstructured":"Sun, W., et al.: Worldplay: towards long-term geometric consistency for real-time interactive world model. arXiv preprint (2025)"},{"key":"10_CR45","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"10_CR46","doi-asserted-by":"crossref","unstructured":"Wang, H., et\u00a0al.: 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"},{"key":"10_CR47","unstructured":"Wu, J., et al.: Vmoba: mixture-of-block attention for video diffusion models. arXiv preprint arXiv:2506.23858 (2025)"},{"key":"10_CR48","doi-asserted-by":"publisher","first-page":"62732","DOI":"10.52202\/079017-2006","volume":"37","author":"J Wu","year":"2024","unstructured":"Wu, J., Wang, H., Shang, Y., Shah, M., Yan, Y.: Ptq4dit: post-training quantization for diffusion transformers. Adv. Neural. Inf. Process. Syst. 37, 62732\u201362755 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR49","unstructured":"Wu, X., Wang, H., Zhou, Y., Lu, Q.: Usv: unified sparsification for accelerating video diffusion models. arXiv preprint arXiv:2512.05754 (2025)"},{"key":"10_CR50","unstructured":"Xi, H., et\u00a0al.: Quant videogen: auto-regressive long video generation via 2-bit kv-cache quantization. arXiv preprint arXiv:2602.02958 (2026)"},{"key":"10_CR51","unstructured":"Xi, H., et al.: Sparse videogen: accelerating video diffusion transformers with spatial-temporal sparsity (2025)"},{"key":"10_CR52","doi-asserted-by":"crossref","unstructured":"Xia, Y., et al.: Training-free and adaptive sparse attention for efficient long video generation (2025)","DOI":"10.1109\/ICCV51701.2025.01483"},{"key":"10_CR53","unstructured":"Yang, S., et al.: Longlive: real-time interactive long video generation. arXiv preprint arXiv:2509.22622 (2025)"},{"key":"10_CR54","doi-asserted-by":"crossref","unstructured":"Yang, S., et\u00a0al.: Sparse videogen2: Accelerate video generation with sparse attention via semantic-aware permutation. arXiv preprint arXiv:2505.18875 (2025)","DOI":"10.52202\/085713-3243"},{"key":"10_CR55","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":"10_CR56","doi-asserted-by":"crossref","unstructured":"Yin, T., Gharbi, M., Zhang, R., Shechtman, E., Durand, F., Freeman, W.T., Park, T.: 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":"10_CR57","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":"10_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Ditfastattnv2: head-wise attention compression for multi-modality diffusion transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 16399\u201316409 (2025)","DOI":"10.1109\/ICCV51701.2025.01522"},{"key":"10_CR59","unstructured":"Zhang, J., et al.: Sagebwd: a trainable low-bit attention. arXiv preprint arXiv:2603.02170 (2026)"},{"key":"10_CR60","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 (ICML) (2025)"},{"key":"10_CR61","unstructured":"Zhang, Jet al.: Spargeattention2: trainable sparse attention via hybrid top-k+ top-p masking and distillation fine-tuning. arXiv preprint arXiv:2602.13515 (2026)"},{"key":"10_CR62","unstructured":"Zhang, J., et\u00a0al.: Efficient attention methods: hardware-efficient, sparse, compact, and linear attention (2025). https:\/\/attention-survey.github.io\/files\/Attention_Survey.pdf. Accessed 27 June 2026"},{"key":"10_CR63","unstructured":"Zhang, J., et\u00a0al.: Sla: beyond sparsity in diffusion transformers via fine-tunable sparse-linear attention. arXiv preprint arXiv:2509.24006 (2025)"},{"key":"10_CR64","unstructured":"Zhang, J., et al.: Sla2: sparse-linear attention with learnable routing and qat. arXiv preprint arXiv:2602.12675 (2026)"},{"key":"10_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Sageattention3: microscaling fp4 attention for inference and an exploration of 8-bit training. arXiv preprint arXiv:2505.11594 (2025)","DOI":"10.52202\/085713-1799"},{"key":"10_CR66","unstructured":"Zhang, J., Wei, J., Zhang, P., Zhu, J., Chen, J.: Sageattention: accurate 8-bit attention for plug-and-play inference acceleration. In: International Conference on Learning Representations (ICLR) (2025)"},{"key":"10_CR67","unstructured":"Zhang, J., et al.: Spargeattention: accurate and training-free sparse attention accelerating any model inference. arXiv preprint arXiv:2502.18137 (2025)"},{"key":"10_CR68","unstructured":"Zhang, J., et al.: Sageattention2++: a more efficient implementation of sageattention2. arXiv preprint arXiv:2505.21136 (2025)"},{"key":"10_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: Vsa: faster video diffusion with trainable sparse attention. arXiv preprint arXiv:2505.13389 (2025)","DOI":"10.52202\/085713-5099"},{"key":"10_CR70","doi-asserted-by":"crossref","unstructured":"Zhao, T., et\u00a0al.: Paroattention: pattern-aware reordering for efficient sparse and quantized attention in visual generation models. arXiv preprint arXiv:2506.16054 (2025)","DOI":"10.52202\/085713-4218"},{"key":"10_CR71","unstructured":"Zheng, K., et al.: Large scale diffusion distillation via score-regularized continuous-time consistency. arXiv preprint arXiv:2510.08431 (2025)"},{"key":"10_CR72","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\/978-3-032-37359-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:15Z","timestamp":1788934035000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37359-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373588","9783032373595"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37359-5_10","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"}}]}}