{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T21:28:46Z","timestamp":1772918926132,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11132479","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":3,"title":["ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression"],"prefix":"10.1109","author":[{"given":"Guangda","family":"Liu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,School of Computer Science"}]},{"given":"Chengwei","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Computer Science"}]},{"given":"Jieru","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Computer Science"}]},{"given":"Chenqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Computer Science"}]},{"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Computer Science"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"ref2","article-title":"SWE-bench: Can language models resolve realworld github issues?","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jimenez"},{"key":"ref3","article-title":"Openai o1 system card","year":"2024"},{"key":"ref4","article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023"},{"key":"ref5","article-title":"How long can open-source llms truly promise on context length?","author":"Li","year":"2023"},{"key":"ref6","article-title":"Gpt-4o system card","year":"2024"},{"key":"ref7","article-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","author":"GLM","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref9","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2024","journal-title":"ICLR"},{"key":"ref10","first-page":"34661","article-title":"H2o: Heavy-hitter oracle for efficient generative inference of large language models","volume":"36","author":"Zhang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"Snapkv: Llm knows what you are looking for before generation","author":"Li","year":"2024"},{"key":"ref12","article-title":"Keyformer: Kv cache reduction through key tokens selection for efficient generative inference","author":"Adnan","year":"2024","journal-title":"MLSys"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/ISCA59077.2024.00077","article-title":"Alisa: Accelerating large language model inference via sparsity-aware kv caching","author":"Zhao","year":"2024"},{"key":"ref14","article-title":"Inf-mllm: Efficient streaming inference of multimodal large language models on a single gpu","author":"Ning","year":"2024"},{"key":"ref15","article-title":"Quest: Query-aware sparsity for efficient long-context llm inference","author":"Tang","year":"2024","journal-title":"ICML"},{"key":"ref16","article-title":"Attention is all you need","author":"Vaswani","year":"2023"},{"key":"ref17","article-title":"Infinibench: A comprehensive benchmark for large multimodal models in very long video understanding","author":"Ataallah","year":"2024"},{"key":"ref18","first-page":"155","article-title":"InfiniGen: Efficient generative inference of large language models with dynamic KV cache management","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Lee"},{"key":"ref19","article-title":"Kivi: A tuning-free asymmetric 2bit quantization for kv cache","author":"Liu","year":"2024","journal-title":"ICML"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.ins.2022.11.139","article-title":"K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data","volume":"622","author":"Ikotun","year":"2023","journal-title":"Information Sciences"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"ref22","article-title":"Compressive transformers for long-range sequence modelling","author":"Rae","year":"2019"},{"key":"ref23","article-title":"Flexgen: High-throughput generative inference of large language models with a single gpu","author":"Sheng","year":"2023"},{"key":"ref24","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11132479.pdf?arnumber=11132479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:31:05Z","timestamp":1758000665000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132479\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11132479","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}