{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T01:05:44Z","timestamp":1784163944324,"version":"3.55.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"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":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571467","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-10","source":"Crossref","is-referenced-by-count":2,"title":["Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation"],"prefix":"10.1109","author":[{"given":"Xutong","family":"Liu","sequence":"first","affiliation":[{"name":"University of Washington"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baran","family":"Atalar","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangxiang","family":"Dai","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhang","family":"Zuo","sequence":"additional","affiliation":[{"name":"City University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John C.S.","family":"Lui","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlee","family":"Joe-Wong","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363447"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2577"},{"key":"ref3","article-title":"Offline learning for combinatorial multi-armed bandits","author":"Liu","year":"2025"},{"key":"ref4","article-title":"Meancache: User-centric semantic cache for large language model based web services","author":"Gill","year":"2024"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.nlposs-1.24","article-title":"Gptcache: An open-source semantic cache for llm applications enabling faster answers and cost savings","volume-title":"Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)","author":"Bang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682957"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2198"},{"key":"ref9","first-page":"38 087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International conference on machine learning","author":"Xiao"},{"key":"ref10","first-page":"19 274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"International Conference on Machine Learning","author":"Leviathan"},{"key":"ref11","article-title":"Accelerating llm inference with staged speculative decoding","author":"Spector","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640411"},{"key":"ref13","first-page":"135","article-title":"{ServerlessLLM}:{Low-Latency} serverless inference for large language models","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Fu"},{"key":"ref14","article-title":"Efficiently scaling transformer inference","author":"Pope","year":"2022"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1145\/3600006.3613165","article-title":"Efficient memory management for large language model serving with pagedattention","volume-title":"Proceedings of the 29th Symposium on Operating Systems Principles","author":"Kwon"},{"key":"ref16","article-title":"High-throughput generative inference of large language models with a single gpu","volume-title":"International Conference on Machine Learning","author":"Sheng"},{"key":"ref17","article-title":"Prompt cache: Modular attention reuse for low-latency inference","author":"Gim","year":"2023"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.36227\/techrxiv.172115025.57884352\/v1","article-title":"Mobile edge intelligence for large language models: A contemporary survey","author":"Qu","year":"2024"},{"key":"ref19","article-title":"Cost-effective online multi-llm selection with versatile reward models","author":"Dai","year":"2024"},{"key":"ref20","article-title":"Graphrouter: A graph-based router for llm selections","author":"Feng","year":"2024"},{"key":"ref21","first-page":"151","article-title":"Combinatorial multi-armed bandit: General framework and applications","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref22","first-page":"1161","article-title":"Improving regret bounds for combinatorial semi-bandits with probabilistically triggered arms and its applications","author":"Wang","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1084"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2001.970573"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2004.11.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29425"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526769"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1559795.1559815"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155221"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-024-00864-x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-218X(00)00366-8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TON.2024.3519568"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736824"},{"key":"ref35","first-page":"22 559","article-title":"Contextual combinatorial bandits with probabilistically triggered arms","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1410","article-title":"Sentence-bert: Sentence embeddings using siamese bert-networks","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing","author":"Reimers"},{"key":"ref37","first-page":"37","article-title":"The maximum vertex coverage problem on bipartite graphs","volume-title":"Discrete Appl. Math.","volume":"165","author":"Apollonio","year":"2014"},{"key":"ref38","article-title":"Inequalities for the l1 deviation of the empirical distribution","volume-title":"Hewlett-Packard Labs, Tech. Rep","author":"Weissman","year":"2003"},{"key":"ref39","first-page":"2607","article-title":"Multinomial logit bandit with low switching cost","volume-title":"International Conference on Machine Learning","author":"Dong"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571467.pdf?arnumber=11571467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:16:37Z","timestamp":1782796597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571467\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571467","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}