{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:03:34Z","timestamp":1775840614209,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62476126"],"award-info":[{"award-number":["62476126"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792922","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:34Z","timestamp":1775771674000},"page":"8609-8612","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking MoE with Retrieval-Memory Synergy: Towards Efficient Expert Coordination"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3937-7967","authenticated-orcid":false,"given":"Wanjie","family":"Tao","sequence":"first","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4618-7299","authenticated-orcid":false,"given":"Qun","family":"Dai","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0245-7104","authenticated-orcid":false,"given":"Yantong","family":"Lv","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4115-3068","authenticated-orcid":false,"given":"Quan","family":"Lu","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4549-6372","authenticated-orcid":false,"given":"Ning","family":"Jiang","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0807-6889","authenticated-orcid":false,"given":"Zulong","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Damai Dai Chengqi Deng Chenggang Zhao R.X. Xu Huazuo Gao Deli Chen Jiashi Li Wangding Zeng Xingkai Yu Y. Wu et al. 2024. DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models. arXiv preprint arXiv:2401.06066 (2024).","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference. 422-428","author":"Eric Mihail","year":"2020","unstructured":"Mihail Eric, Rahul Goel, Shachi Paul, Adarsh Kumar, Abhishek Sethi, Peter Ku, Anuj Kumar Goyal, Sanchit Agarwal, et al., 2020. A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines. In Proceedings of the 12th Language Resources and Evaluation Conference. 422-428."},{"key":"e_1_3_2_1_3_1","first-page":"1","article-title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. Journal of Machine Learning Research, Vol. 23, 120 (2022), 1-39.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_4_1","first-page":"9155","volume-title":"Harder Tasks Need More Experts: Dynamic Routing in MoE Models. In Findings of the Association for Computational Linguistics: ACL","author":"Huang Quzhe","year":"2024","unstructured":"Quzhe Huang, Zhenwei An, Nan Zhuang, Minghan Chen, Yang Wang, Xihui Liu, and Lin Song. 2024. Harder Tasks Need More Experts: Dynamic Routing in MoE Models. In Findings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics, 9155-9170."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Khandelwal Urvashi","year":"2020","unstructured":"Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2020. Generalization through Memorization: Nearest Neighbor Language Models. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_7_1","first-page":"9459","article-title":". Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Petroni, et al., 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 33. 9459-9474.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Puigcerver Joan","year":"2024","unstructured":"Joan Puigcerver, Carlos Riquelme, Basil Mustafa, and Neil Houlsby. 2024. From Sparse to Soft Mixtures of Experts. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_9_1","first-page":"17555","article-title":"Hash Layers For Large Sparse Models","volume":"34","author":"Roller Stephen","year":"2021","unstructured":"Stephen Roller, Sainbayar Sukhbaatar, and Jason Weston. 2021. Hash Layers For Large Sparse Models. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 34. 17555-17566.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_10_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"28","author":"Sukhbaatar Sainbayar","year":"2015","unstructured":"Sainbayar Sukhbaatar, Jason Weston, and Rob Fergus. 2015. End-To-End Memory Networks. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 28."},{"key":"e_1_3_2_1_11_1","volume-title":"Memory Networks. In Proceedings of the International Conference on Learning Representations (ICLR).","author":"Weston Jason","year":"2015","unstructured":"Jason Weston, Sumit Chopra, and Antoine Bordes. 2015. Memory Networks. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_12_1","volume-title":"Memorizing Transformers. In Proceedings of the International Conference on Learning Representations (ICLR).","author":"Wu Yuhuai","year":"2022","unstructured":"Yuhuai Wu, Markus N Rabe, DeLesley Hutchins, and Christian Szegedy. 2022. Memorizing Transformers. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_13_1","volume-title":"Assessing Adaptive Retrieval-Augmented Generation for Open-Domain Question Answering. arXiv preprint arXiv:2402.16457","author":"Zhang Zihan","year":"2024","unstructured":"Zihan Zhang, Mengqi Li, Hayes Ma, Siru Ouyang, Zhiyuan Liu, and Meng Jiang. 2024. Assessing Adaptive Retrieval-Augmented Generation for Open-Domain Question Answering. arXiv preprint arXiv:2402.16457 (2024)."},{"key":"e_1_3_2_1_14_1","first-page":"7103","article-title":". Mixture-of-Experts with Expert Choice Routing","volume":"35","author":"Zhou Yanqi","year":"2022","unstructured":"Yanqi Zhou, Tao Lei, Hanxiao Liu, Nan Du, Yanping Huang, Vincent Zhao, Andrew M Dai, Quoc V Le, James Laudon, et al., 2022. Mixture-of-Experts with Expert Choice Routing. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 35. 7103-7114.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:14:16Z","timestamp":1775837656000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":14,"alternative-id":["10.1145\/3774904.3792922","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792922","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}