{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T08:04:25Z","timestamp":1784189065072,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":11,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234165","type":"print"},{"value":"9789819234172","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3417-2_19","type":"book-chapter","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:11:56Z","timestamp":1784185916000},"page":"214-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SieveKV: Semantic Multi-signal Eviction for Long-Context Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2439-4387","authenticated-orcid":false,"given":"Kuo","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"19_CR1","unstructured":"AI, M.L lama: Llama 3.2 model card. Tech. rep. (2024), https:\/\/github.com\/meta-llama\/llama-models"},{"key":"19_CR2","doi-asserted-by":"publisher","first-page":"4895","DOI":"10.18653\/v1\/2023.emnlp-main.298","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"J Ainslie","year":"2023","unstructured":"Ainslie, J., Lee-Thorp, J., de Jong, M., Zemlyanskiy, Y., Lebr\u00f3n, F., Sanghai, S.: Gqa: Training generalized multi-query transformer models from multi-head checkpoints. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 4895\u20134901 (2023)"},{"key":"19_CR3","first-page":"1270","volume-title":"Advances in Neural Information Processing Systems","author":"C Hooper","year":"2024","unstructured":"Hooper, C., et al.: Kvquant: Towards 10 million context length llm inference with kv cache quantization. In: Advances in Neural Information Processing Systems, vol. 37, pp. 1270\u20131303 (2024)"},{"key":"19_CR4","volume-title":"Proceedings of the First Conference on Language Modeling (COLM 2024)","author":"CP Hsieh","year":"2024","unstructured":"Hsieh, C.P., et al.: Ruler: What\u2019s the real context size of your long-context language models? In: Proceedings of the First Conference on Language Modeling (COLM 2024) (2024)"},{"key":"19_CR5","volume-title":"Advances in Neural Information Processing Systems","author":"JH Kim","year":"2025","unstructured":"Kim, J.H., Kim, J., Kwon, S., Lee, J.W., Yun, S., Song, H.O.: Kvzip: Query-agnostic kv cache compression with context reconstruction. In: Advances in Neural Information Processing Systems (2025)"},{"key":"19_CR6","first-page":"22947","volume-title":"Advances in Neural Information Processing Systems","author":"Y Li","year":"2024","unstructured":"Li, Y., et al.: Snapkv: Llm knows what you are looking for before generation. In: Advances in Neural Information Processing Systems, vol. 37, pp. 22947\u201322970 (2024)"},{"key":"19_CR7","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1162\/tacl_a_00638","volume":"12","author":"NF Liu","year":"2024","unstructured":"Liu, N.F., et al.: Lost in the middle: How language models use long contexts. Trans. Assoc. Comput. Linguist. 12, 157\u2013173 (2024)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"19_CR8","first-page":"32332","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Z Liu","year":"2024","unstructured":"Liu, Z., et al.: Kivi: A tuning-free asymmetric 2-bit quantization for kv cache. In: Proceedings of the 41st International Conference on Machine Learning, vol. 235, pp. 32332\u201332344 (2024)"},{"key":"19_CR9","unstructured":"Team, Q.: Qwen2.5 technical report. arXiv preprint arXiv:2412.15115 (2025)"},{"key":"19_CR10","volume-title":"Proceedings of the International Conference on Learning Representations","author":"G Xiao","year":"2024","unstructured":"Xiao, G., Tian, Y., Chen, B., Han, S., Lewis, M.: Efficient streaming language models with attention sinks. In: Proceedings of the International Conference on Learning Representations (2024)"},{"key":"19_CR11","first-page":"34661","volume-title":"Advances in Neural Information Processing Systems","author":"Z Zhang","year":"2023","unstructured":"Zhang, Z., et al.: H2o: Heavy-hitter oracle for efficient generative inference of large language models. In: Advances in Neural Information Processing Systems, vol. 36, pp. 34661\u201334710 (2023)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3417-2_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:11:58Z","timestamp":1784185918000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3417-2_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"ISBN":["9789819234165","9789819234172"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3417-2_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]},"assertion":[{"value":"17 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}