{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T13:02:28Z","timestamp":1785502948053,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0203700"],"award-info":[{"award-number":["2024YFE0203700"]}]},{"name":"National Natural Science Foundation of China","award":["62376243"],"award-info":[{"award-number":["62376243"]}]},{"name":"\"Pioneer\" and \"Leading Goose\" R&D Program of Zhejiang","award":["2025C02037"],"award-info":[{"award-number":["2025C02037"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780222","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"1998-2009","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-task Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1460-2777","authenticated-orcid":false,"given":"Ziyu","family":"Zhao","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China and Shanghai Innovation Institute, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0396-6220","authenticated-orcid":false,"given":"Yixiao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China and Shanghai Innovation Institute, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8409-9111","authenticated-orcid":false,"given":"Xin","family":"Yu","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University, State College, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0249-1678","authenticated-orcid":false,"given":"Zhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Seed, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6892-5357","authenticated-orcid":false,"given":"Didi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0819-9782","authenticated-orcid":false,"given":"Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0831-3549","authenticated-orcid":false,"given":"Zexi","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1844-7029","authenticated-orcid":false,"given":"Jinluan","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3363-570X","authenticated-orcid":false,"given":"Xuwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance Seed, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0572-9194","authenticated-orcid":false,"given":"Jing","family":"Su","sequence":"additional","affiliation":[{"name":"Bytedance Seed, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7528-8131","authenticated-orcid":false,"given":"Kun","family":"Kuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3789-8507","authenticated-orcid":false,"given":"Zhongyu","family":"Wei","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7901-8662","authenticated-orcid":false,"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al., 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_2_2_1","first-page":"578","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, et al., 2018. : An automated optimizing compiler for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 578-594."},{"key":"e_1_3_2_2_3_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_2_4_1","volume-title":"Sparse low-rank adaptation of pre-trained language models. arXiv preprint arXiv:2311.11696","author":"Ding Ning","year":"2023","unstructured":"Ning Ding, Xingtai Lv, Qiaosen Wang, Yulin Chen, Bowen Zhou, Zhiyuan Liu, and Maosong Sun. 2023. Sparse low-rank adaptation of pre-trained language models. arXiv preprint arXiv:2311.11696 (2023)."},{"key":"e_1_3_2_2_5_1","unstructured":"Shihan Dou Enyu Zhou Yan Liu Songyang Gao Jun Zhao Wei Shen Yuhao Zhou Zhiheng Xi Xiao Wang Xiaoran Fan Shiliang Pu Jiang Zhu Rui Zheng Tao Gui Qi Zhang and Xuanjing Huang. 2023. LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment. arXiv:2312.09979 [cs.CL]"},{"key":"e_1_3_2_2_6_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_2_7_1","volume-title":"Mixture-of-loras: An efficient multitask tuning for large language models. arXiv preprint arXiv:2403.03432","author":"Feng Wenfeng","year":"2024","unstructured":"Wenfeng Feng, Chuzhan Hao, Yuewei Zhang, Yu Han, and Hao Wang. 2024. Mixture-of-loras: An efficient multitask tuning for large language models. arXiv preprint arXiv:2403.03432 (2024)."},{"key":"e_1_3_2_2_8_1","volume-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey. arXiv preprint arXiv:2403.14608","author":"Han Zeyu","year":"2024","unstructured":"Zeyu Han, Chao Gao, Jinyang Liu, Jeff Zhang, and Sai Qian Zhang. 2024. Parameter-efficient fine-tuning for large models: A comprehensive survey. arXiv preprint arXiv:2403.14608 (2024)."},{"key":"e_1_3_2_2_9_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_2_10_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al., 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_2_11_1","volume-title":"Mixlora: Enhancing large language models fine-tuning with lora based mixture of experts. arXiv preprint arXiv:2404.15159","author":"Li Dengchun","year":"2024","unstructured":"Dengchun Li, Yingzi Ma, Naizheng Wang, Zhiyuan Cheng, Lei Duan, Jie Zuo, Cal Yang, and Mingjie Tang. 2024. Mixlora: Enhancing large language models fine-tuning with lora based mixture of experts. arXiv preprint arXiv:2404.15159 (2024)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0142"},{"key":"e_1_3_2_2_13_1","volume-title":"Moelora: An moe-based parameter efficient fine-tuning method for multi-task medical applications. arXiv preprint arXiv:2310.18339","author":"Liu Qidong","year":"2023","unstructured":"Qidong Liu, Xian Wu, Xiangyu Zhao, Yuanshao Zhu, Derong Xu, Feng Tian, and Yefeng Zheng. 2023a. Moelora: An moe-based parameter efficient fine-tuning method for multi-task medical applications. arXiv preprint arXiv:2310.18339 (2023)."},{"key":"e_1_3_2_2_14_1","volume-title":"GPT understands, too. AI Open","author":"Liu Xiao","year":"2023","unstructured":"Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2023b. GPT understands, too. AI Open (2023)."},{"key":"e_1_3_2_2_15_1","volume-title":"Yi Tay, Denny Zhou, Quoc V Le, Barret Zoph, Jason Wei, et al.","author":"Longpre Shayne","year":"2023","unstructured":"Shayne Longpre, Le Hou, Tu Vu, Albert Webson, Hyung Won Chung, Yi Tay, Denny Zhou, Quoc V Le, Barret Zoph, Jason Wei, et al., 2023. The Flan Collection: Designing Data and Methods for Effective Instruction Tuning. arXiv preprint arXiv:2301.13688 (2023)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40663-9"},{"key":"e_1_3_2_2_17_1","volume-title":"Soft Merging of Experts with Adaptive Routing. arXiv preprint arXiv:2306.03745","author":"Muqeeth Mohammed","year":"2023","unstructured":"Mohammed Muqeeth, Haokun Liu, and Colin Raffel. 2023. Soft Merging of Experts with Adaptive Routing. arXiv preprint arXiv:2306.03745 (2023)."},{"key":"e_1_3_2_2_18_1","volume-title":"Barret Zoph, William Fedus, Xinyun Chen, et al.","author":"Shen Sheng","year":"2023","unstructured":"Sheng Shen, Le Hou, Yanqi Zhou, Nan Du, Shayne Longpre, Jason Wei, Hyung Won Chung, Barret Zoph, William Fedus, Xinyun Chen, et al., 2023. Mixture-of-experts meets instruction tuning: A winning combination for large language models. arXiv preprint arXiv:2305.14705 (2023)."},{"key":"e_1_3_2_2_19_1","volume-title":"HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning. arXiv preprint arXiv:2404.19245","author":"Tian Chunlin","year":"2024","unstructured":"Chunlin Tian, Zhan Shi, Zhijiang Guo, Li Li, and Chengzhong Xu. 2024. HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning. arXiv preprint arXiv:2404.19245 (2024)."},{"key":"e_1_3_2_2_20_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_21_1","volume-title":"Auxiliary-loss-free load balancing strategy for mixture-of-experts. arXiv preprint arXiv:2408.15664","author":"Wang Lean","year":"2024","unstructured":"Lean Wang, Huazuo Gao, Chenggang Zhao, Xu Sun, and Damai Dai. 2024. Auxiliary-loss-free load balancing strategy for mixture-of-experts. arXiv preprint arXiv:2408.15664 (2024)."},{"key":"e_1_3_2_2_22_1","volume-title":"Pushing mixture of experts to the limit: Extremely parameter efficient moe for instruction tuning. arXiv preprint arXiv:2309.05444","author":"Zadouri Ted","year":"2023","unstructured":"Ted Zadouri, Ahmet \u00dcst\u00fcn, Arash Ahmadian, Beyza Ermi\u015f, Acyr Locatelli, and Sara Hooker. 2023. Pushing mixture of experts to the limit: Extremely parameter efficient moe for instruction tuning. arXiv preprint arXiv:2309.05444 (2023)."},{"key":"e_1_3_2_2_23_1","volume-title":"AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning. arXiv preprint arXiv:2303.10512","author":"Zhang Qingru","year":"2023","unstructured":"Qingru Zhang, Minshuo Chen, Alexander Bukharin, Nikos Karampatziakis, Pengcheng He, Yu Cheng, Weizhu Chen, and Tuo Zhao. 2023a. AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning. arXiv preprint arXiv:2303.10512 (2023)."},{"key":"e_1_3_2_2_24_1","unstructured":"Shengyu Zhang Linfeng Dong Xiaoya Li Sen Zhang Xiaofei Sun Shuhe Wang Jiwei Li Runyi Hu Tianwei Zhang Fei Wu et al. 2023b. Instruction tuning for large language models: A survey. arXiv preprint arXiv:2308.10792 (2023)."},{"key":"e_1_3_2_2_25_1","volume-title":"LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild. arXiv preprint arXiv:2402.09997","author":"Zhao Ziyu","year":"2024","unstructured":"Ziyu Zhao, Leilei Gan, Guoyin Wang, Wangchunshu Zhou, Hongxia Yang, Kun Kuang, and Fei Wu. 2024a. LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild. arXiv preprint arXiv:2402.09997 (2024)."},{"key":"e_1_3_2_2_26_1","volume-title":"Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering. arXiv preprint arXiv:2409.16167","author":"Zhao Ziyu","year":"2024","unstructured":"Ziyu Zhao, Tao Shen, Didi Zhu, Zexi Li, Jing Su, Xuwu Wang, Kun Kuang, and Fei Wu. 2024b. Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering. arXiv preprint arXiv:2409.16167 (2024)."},{"key":"e_1_3_2_2_27_1","unstructured":"Yun Zhu Nevan Wichers Chu-Cheng Lin Xinyi Wang Tianlong Chen Lei Shu Han Lu Canoee Liu Liangchen Luo Jindong Chen et al. 2023. SiRA: Sparse Mixture of Low Rank Adaptation. arXiv preprint arXiv:2311.09179 (2023)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:13:58Z","timestamp":1785500038000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":27,"alternative-id":["10.1145\/3770854.3780222","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780222","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}