{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:43:29Z","timestamp":1763192609019,"version":"3.45.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228559","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["MiDream: Multi-Domain Retrieval Enhancement with Mixture-of-Experts"],"prefix":"10.1109","author":[{"given":"Kehui","family":"Tan","sequence":"first","affiliation":[{"name":"South China Normal University,China"}]},{"given":"Wenjing","family":"Pang","sequence":"additional","affiliation":[{"name":"South China Normal University,China"}]},{"given":"Jiayang","family":"Yao","sequence":"additional","affiliation":[{"name":"South China Normal University,China"}]},{"given":"Tianqi","family":"Pang","sequence":"additional","affiliation":[{"name":"South China Normal University,China"}]},{"given":"Xiangyang","family":"Liu","sequence":"additional","affiliation":[{"name":"South China Normal University,China"}]},{"given":"Chenyou","family":"Fan","sequence":"additional","affiliation":[{"name":"South China Normal University,China"}]}],"member":"263","reference":[{"journal-title":"Gpt-4 technical report","year":"2023","key":"ref1"},{"year":"2024","key":"ref2","article-title":"Llama 3 model card"},{"article-title":"Do large language models know about facts?","year":"2023","author":"Hu","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.463"},{"article-title":"Retrieval-augmented generation for ai-generated content: A survey","year":"2024","author":"Zhao","key":"ref5"},{"article-title":"Retrieval-augmented generation for large language models: A survey","year":"2023","author":"Gao","key":"ref6"},{"article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","year":"2017","author":"Shazeer","key":"ref7"},{"key":"ref8","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"International conference on machine learning","author":"Dauphin"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.286"},{"article-title":"Paperqa: Retrieval-augmented generative agent for scientific research","year":"2023","author":"L\u00e1la","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531736"},{"key":"ref13","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.949"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/coli.a.16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888956"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM62325.2024.10822374"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICETCI61221.2024.10594504"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111332"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.65"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657834"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3701228"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.981"},{"article-title":"Richrag: Crafting rich responses for multi-faceted queries in retrieval-augmented generation","year":"2024","author":"Wang","key":"ref25"},{"key":"ref26","article-title":"Fedjets: Efficient just-in-time personalization with federated mixture of experts","author":"Dun","year":"2023","journal-title":"R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Large Foundation Models"},{"article-title":"Branch-train-merge: Embarrassingly parallel training of expert language models","year":"2022","author":"Li","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00312"},{"article-title":"Moral: Moe augmented lora for llms\u2019 lifelong learning","year":"2024","author":"Yang","key":"ref29"},{"article-title":"Mixture-of-experts meets instruction tuning: A winning combination for large language models","year":"2023","author":"Shen","key":"ref30"},{"key":"ref31","article-title":"To repeat or not to repeat: Insights from scaling llm under token-crisis","volume":"36","author":"Xue","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Pushing mixture of experts to the limit: Extremely parameter efficient moe for instruction tuning","year":"2023","author":"Zadouri","key":"ref32"},{"article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","year":"2020","author":"Lepikhin","key":"ref33"},{"issue":"8","key":"ref34","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"article-title":"Gaussian error linear units (gelus)","year":"2016","author":"Hendrycks","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3130348.3130374"},{"article-title":"Unsupervised dense information retrieval with contrastive learning","year":"2021","author":"Izacard","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10651011"},{"key":"ref39","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"article-title":"M3e: Moka massive mixed embedding model","year":"2023","author":"Wang","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3618474"},{"article-title":"Sgdr: Stochastic gradient descent with warm restarts","year":"2016","author":"Loshchilov","key":"ref43"},{"article-title":"Deepseek-v3 technical report","year":"2024","author":"Liu","key":"ref44"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228559.pdf?arnumber=11228559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:40:12Z","timestamp":1763192412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228559","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}