{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:11:51Z","timestamp":1788844311925,"version":"build-2803163510"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China (NSFC)","award":["62302048,U25A20436,62272050"],"award-info":[{"award-number":["62302048,U25A20436,62272050"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/icws72778.2026.00134","type":"proceedings-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:16:09Z","timestamp":1788808569000},"page":"1133-1142","source":"Crossref","is-referenced-by-count":0,"title":["CONCORD: Asynchronous Sparse Aggregation for Device-Cloud Rag Under Document Isolation"],"prefix":"10.1109","author":[{"given":"Xuedong","family":"Hu","sequence":"first","affiliation":[{"name":"Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqing","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Future Networks, Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Normal University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Future Networks, Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijia","family":"Jia","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Future Networks, Beijing Normal University","place":["Zhuhai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9459","article-title":"Retrievalaugmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"International conference on machine learning","author":"Guu","year":"2020"},{"key":"ref3","article-title":"Generalization through memorization: Nearest neighbor language models","volume-title":"International Conference on Learning Representations","author":"Khandelwal","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"ref5","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"International conference on machine learning","author":"Borgeaud","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.463"},{"key":"ref7","article-title":"Self-rag: Learning to retrieve, generate, and critique through self-reflection","volume-title":"The Twelfth International Conference on Learning Representations","author":"Asai","year":"2024"},{"issue":"251","key":"ref8","first-page":"1","article-title":"Atlas: Few-shot learning with retrieval augmented language models","volume":"24","author":"Izacard","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3229556.3229562"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2947893"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2995583"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS67624.2025.00046"},{"key":"ref16","article-title":"Cost-efficient collaboration between on-device and cloud language models","volume-title":"Forty-second International Conference on Machine Learning","author":"Narayan","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3513457"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3724420"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00105"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3704413.3764419"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3768628"},{"key":"ref22","article-title":"Block-attention for efficient prefilling","volume-title":"International Conference on Learning Representations","author":"Ma","year":"2025"},{"key":"ref23","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"International Conference on Machine Learning","author":"Leviathan","year":"2023"},{"key":"ref24","article-title":"Accelerating large language model decoding with speculative sampling","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3043051"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS49710.2020.00069"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS53863.2021.00040"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3320752"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044557"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044700"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICC52391.2025.11160773"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3562362"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3611379"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2026.3665250"},{"key":"ref35","first-page":"5209","article-title":"Medusa: Simple llm inference acceleration framework with multiple decoding heads","volume-title":"International Conference on Machine Learning","author":"Cai","year":"2024"},{"key":"ref36","article-title":"Speculative streaming: Fast llm inference without auxiliary models","author":"Bhendawade","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Recurrent drafter for fast speculative decoding in large language models","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","first-page":"28935","article-title":"Eagle: Speculative sampling requires rethinking feature uncertainty","volume-title":"International Conference on Machine Learning","author":"Li","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3772052.3772239"},{"key":"ref40","first-page":"193","article-title":"Distserve: Disaggregating prefill and decoding for goodputoptimized large language model serving","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhong","year":"2024"},{"key":"ref41","first-page":"117","article-title":"Taming throughput-latency tradeoff in llm inference with sarathi-serve","volume-title":"18th USENIX symposium on operating systems design and implementation (OSDI 24)","author":"Agrawal","year":"2024"}],"event":{"name":"2026 IEEE International Conference on Web Services (ICWS)","location":"Sydney, Australia","start":{"date-parts":[[2026,7,13]]},"end":{"date-parts":[[2026,7,18]]}},"container-title":["2026 IEEE International Conference on Web Services (ICWS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11670018\/11670022\/11670051.pdf?arnumber=11670051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:52:37Z","timestamp":1788843157000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11670051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icws72778.2026.00134","relation":{},"subject":[],"published":{"date-parts":[[2026,7]]}}}