{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:26:34Z","timestamp":1774419994800,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890716","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["QoKV: Comprehending and Surpassing the Hurdles of KV Cache Quantization"],"prefix":"10.1109","author":[{"given":"Jinguang","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexi","family":"Yin","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingting","family":"Yang","sequence":"additional","affiliation":[{"name":"PengCheng Laboratory,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Qi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zirui","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"18878","article-title":"Data distributional properties drive emer gent in-context learning in transformers","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Chan","year":"2022"},{"issue":"8","key":"ref2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.102"},{"key":"ref4","first-page":"1877","volume":"33","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners. Advances in neural information processing systems"},{"key":"ref5","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref6","author":"Touvron","year":"2023","journal-title":"Open and efficient foundation language models."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref8","article-title":"Efficiently scaling transformer inference","volume-title":"Proceedings of Machine Learning and Systems","volume":"5","author":"Pope"},{"key":"ref9","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao"},{"key":"ref10","article-title":"Rptq: Reorder-based post-training quantization for large language models","author":"Yuan","year":"2023"},{"key":"ref11","article-title":"Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time","author":"Liu","year":"2023"},{"key":"ref12","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020"},{"key":"ref13","article-title":"Mongoose: A learnable lsh framework for efficient neural network training","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref14","article-title":"The pile: An 800gb dataset of diverse text for language modeling","author":"Gao","year":"2020"},{"key":"ref15","author":"Gao","year":"2021","journal-title":"A framework for few-shot language model evaluation"},{"key":"ref16","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075835"},{"issue":"1","key":"ref18","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref19","article-title":"Boolq: Exploring the surprising difficulty of natural yes\/no questions","author":"Clark","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1144"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890716.pdf?arnumber=10890716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:50Z","timestamp":1774416350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890716","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}