{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:11:40Z","timestamp":1789031500769,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370129","type":"print"},{"value":"9783032370136","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\/978-3-032-37013-6_10","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:04:17Z","timestamp":1789031057000},"page":"170-187","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AVQ-Attention: Adaptive Vector-Quantized Attention"],"prefix":"10.1007","author":[{"given":"Winfried van den","family":"Dool","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Forr\u00e9","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Habibian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki M.","family":"Asano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Max","family":"Welling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"10_CR1","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arxiv:2004.05150 (2020). https:\/\/arxiv.org\/abs\/2004.05150"},{"key":"10_CR2","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: Your vit but faster. In: International Conference on Learning Representations (ICLR) 2023 (2022). https:\/\/arxiv.org\/abs\/2210.09461, oral presentation"},{"key":"10_CR3","unstructured":"Bolya, D., Hoffman, J.: Token merging for fast stable diffusion. arXiv preprint arxiv:2303.17604 (2023). https:\/\/arxiv.org\/abs\/2303.17604"},{"key":"10_CR4","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv preprint arxiv:1904.10509. https:\/\/arxiv.org\/abs\/1904.10509 (2019)"},{"key":"10_CR5","unstructured":"Choromanski, K., et al.: Rethinking attention with Performers. In: ICLR (2021). https:\/\/arxiv.org\/abs\/2009.14794"},{"key":"10_CR6","unstructured":"Dao, T.: FlashAttention-2: faster attention with better parallelism and work partitioning. In: ICLR (2024). https:\/\/arxiv.org\/abs\/2307.08691"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Dao, T., Fu, D.Y., Ermon, S., Rudra, A., R\u00e9, C.: Flashattention: fast and memory-efficient exact attention with io-awareness. In: Advances in Neural Information Processing Systems, vol.\u00a035 (2022). https:\/\/arxiv.org\/abs\/2205.14135","DOI":"10.52202\/068431-1189"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10_CR9","unstructured":"van\u00a0den Dool, W., Zhdanov, M., Asano, Y.M., Welling, M.: Adaptive mesh-quantization for neural PDE solvers. arXiv preprint arxiv:2511.18474 (2025). https:\/\/arxiv.org\/abs\/2511.18474"},{"key":"10_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021). https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Hassani, A., Walton, S., Li, J., Li, S., Shi, H.: Neighborhood attention transformer. In: CVPR (2023). https:\/\/arxiv.org\/abs\/2204.07143","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"10_CR12","unstructured":"He, Y., et al.: ScaleCrafter: tuning-free higher-resolution visual generation with diffusion models. In: ICLR (2024). https:\/\/arxiv.org\/abs\/2310.07702"},{"key":"10_CR13","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS (2017). https:\/\/arxiv.org\/abs\/1706.08500"},{"key":"10_CR14","unstructured":"Hooper, C., et al.: Squeezed attention: accelerating long context length LLM inference. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) (2025). https:\/\/arxiv.org\/abs\/2411.09688"},{"key":"10_CR15","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive transformers with linear attention. In: ICML (2020). https:\/\/arxiv.org\/abs\/2006.16236"},{"key":"10_CR16","unstructured":"Kitaev, N., Kaiser, \u0141., Levskaya, A.: Reformer: the efficient transformer. In: ICLR (2020). https:\/\/arxiv.org\/abs\/2001.04451"},{"key":"10_CR17","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":"10_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV (2014). https:\/\/arxiv.org\/abs\/1405.0312","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10_CR19","unstructured":"Lingle, L.D.: Transformer-vq: linear-time transformers via vector quantization. In: International Conference on Learning Representations, vol. 2024, pp. 6121\u20136150 (2024)"},{"key":"10_CR20","unstructured":"Liu, S., Yu, W., Tan, Z., Wang, X.: LinFusion: 1 GPU, 1 minute, 16K image. arXiv preprint arXiv:2409.02097 (2024). https:\/\/arxiv.org\/abs\/2409.02097"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021). https:\/\/arxiv.org\/abs\/2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"2","key":"10_CR22","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"SP Lloyd","year":"1982","unstructured":"Lloyd, S.P.: Least squares quantization in PCM. IEEE Trans. Inf. Theory 28(2), 129\u2013137 (1982)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"10_CR23","unstructured":"Mao, Y., Wang, Q., Ester, M., Li, K.: IceCache: memory-efficient KV-cache management for long-sequence LLMs. In: ICLR (2026). https:\/\/arxiv.org\/abs\/2604.10539"},{"key":"10_CR24","unstructured":"Milakov, M., Gimelshein, N.: Online normalizer calculation for softmax. arXiv preprint arXiv:1805.02867 (2018). https:\/\/arxiv.org\/abs\/1805.02867"},{"key":"10_CR25","unstructured":"van\u00a0den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: NeurIPS (2017). https:\/\/arxiv.org\/abs\/1711.00937"},{"key":"10_CR26","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021). https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"10_CR27","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV, pp. 12179\u201312188 (2021). https:\/\/arxiv.org\/abs\/2103.13413"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022). https:\/\/arxiv.org\/abs\/2112.10752","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10_CR29","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1162\/tacl_a_00353","volume":"9","author":"A Roy","year":"2021","unstructured":"Roy, A., Saffar, M., Vaswani, A., Grangier, D.: Efficient content-based sparse attention with routing transformers. Trans. Assoc. Comput. Linguist. 9, 53\u201368 (2021)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Tang, C., et al.: Mixed-precision neural network quantization via learned layer-wise importance. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20083-0_16"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Tillet, P., Kung, H.T., Cox, D.: Triton: an intermediate language and compiler for tiled neural network computations. In: Proceedings of the 3rd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages (MAPL), pp. 10\u201319 (2019)","DOI":"10.1145\/3315508.3329973"},{"key":"10_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS. pp. 5998\u20136008 (2017). https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"10_CR33","unstructured":"\u010cerven\u00fd, J.: Gilbert: Generalized Hilbert (\u201cGilbert\u201d) space-filling curve for rectangular domains of arbitrary (non-power of two) sizes. https:\/\/github.com\/jakubcerveny\/gilbert (2018). gitHub repository"},{"key":"10_CR34","unstructured":"Vyas, A., Katharopoulos, A., Fleuret, F.: Fast transformers with clustered attention. In: Advances in Neural Information Processing Systems (NeurIPS) (2020). https:\/\/arxiv.org\/abs\/2007.04825, arXiv:2007.04825"},{"issue":"4","key":"10_CR35","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1145\/103085.103089","volume":"34","author":"GK Wallace","year":"1991","unstructured":"Wallace, G.K.: The JPEG still picture compression standard. Commun. ACM 34(4), 30\u201344 (1991)","journal-title":"Commun. ACM"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: HAQ: hardware-aware automated quantization with mixed precision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8612\u20138620 (2019)","DOI":"10.1109\/CVPR.2019.00881"},{"key":"10_CR37","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020). https:\/\/arxiv.org\/abs\/2006.04768"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Yuan, J., et\u00a0al.: Native sparse attention: hardware-aligned and natively trainable sparse attention. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 23078\u201323097 (2025)","DOI":"10.18653\/v1\/2025.acl-long.1126"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: H$$_2$$O: heavy-hitter oracle for efficient generative inference of large language models. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)","DOI":"10.52202\/075280-1506"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"}],"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\/978-3-032-37013-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:04:36Z","timestamp":1789031076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37013-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370129","9783032370136"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37013-6_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":"11 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"}}]}}