{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:06:56Z","timestamp":1784138816433,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808410","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"5082-5086","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["RecGPT-Mobile: On-Device Large Language Models for User Intent Understanding in Taobao Feed Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4269-1101","authenticated-orcid":false,"given":"Bin","family":"Zhang","sequence":"first","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0902-8367","authenticated-orcid":false,"given":"Weipeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1370-1968","authenticated-orcid":false,"given":"Dimin","family":"Wang","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4683-3168","authenticated-orcid":false,"given":"Jialin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1665-3025","authenticated-orcid":false,"given":"Yuning","family":"Jiang","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0498-7491","authenticated-orcid":false,"given":"Zhaode","family":"Wang","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZHou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4918-7425","authenticated-orcid":false,"given":"Chengfei","family":"Lv","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZHou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1590-2113","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZHou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9507-4820","authenticated-orcid":false,"given":"Qichao","family":"Ma","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZHou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7980-4361","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZHou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9633-8569","authenticated-orcid":false,"given":"Junqing","family":"Wu","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZHou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4212-0153","authenticated-orcid":false,"given":"Yipeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba, HangZHou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_4_1","volume-title":"Onerec: Unifying retrieve and rank with generative recommender and iterative preference alignment. arXiv preprint arXiv:2502.18965","author":"Deng Jiaxin","year":"2025","unstructured":"Jiaxin Deng, Shiyao Wang, Kuo Cai, Lejian Ren, Qigen Hu, Weifeng Ding, Qiang Luo, and Guorui Zhou. 2025. Onerec: Unifying retrieve and rank with generative recommender and iterative preference alignment. arXiv preprint arXiv:2502.18965 (2025)."},{"key":"e_1_3_2_1_5_1","volume-title":"int8 (): 8-bit matrix multiplication for transformers at scale. Advances in neural information processing systems 35","author":"Dettmers Tim","year":"2022","unstructured":"Tim Dettmers, Mike Lewis, Younes Belkada, and Luke Zettlemoyer. 2022. Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale. Advances in neural information processing systems 35 (2022), 30318-30332."},{"key":"e_1_3_2_1_6_1","volume-title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. arXiv:2210.17323 [cs.LG] https:\/\/arxiv.org\/abs\/2210.17323","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2023. GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers. arXiv:2210.17323 [cs.LG] https:\/\/arxiv.org\/abs\/2210.17323"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557065"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412700"},{"key":"e_1_3_2_1_9_1","volume-title":"On-device learning with cloud-coordinated data augmentation for extreme model personalization in recommender systems. arXiv preprint arXiv:2201.10382","author":"Gu Renjie","year":"2022","unstructured":"Renjie Gu, Chaoyue Niu, Yikai Yan, FanWu, Shaojie Tang, Rongfeng Jia, Chengfei Lyu, and Guihai Chen. 2022. On-device learning with cloud-coordinated data augmentation for extreme model personalization in recommender systems. arXiv preprint arXiv:2201.10382 (2022)."},{"key":"e_1_3_2_1_10_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_1_11_1","volume-title":"Dally","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William J. Dally. 2015. Learning bothWeights and Connections for Efficient Neural Networks. arXiv:1506.02626 [cs.NE] https: \/\/arxiv.org\/abs\/1506.02626"},{"key":"e_1_3_2_1_12_1","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. arXiv:1503.02531 [stat.ML] https:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_2_1_13_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, LiangWang,Weizhu Chen, et al. 2022. Lora: Low-rank adaptation of large language models. Iclr 1, 2 (2022), 3.","journal-title":"Iclr"},{"key":"e_1_3_2_1_14_1","unstructured":"Aixin Liu Bei Feng Bing Xue BingxuanWang BochaoWu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.718"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3724420"},{"key":"e_1_3_2_1_17_1","volume-title":"MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices. InMMAsia '24Workshops.","author":"Yang Jingbang","year":"2024","unstructured":"ZhaodeWang, Jingbang Yang, Xinyu Qian, Shiwen Xing, Xiaotang Jiang, Chengfei Lv, and Shengyu Zhang. 2024. MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices. InMMAsia '24Workshops."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599878"},{"key":"e_1_3_2_1_19_1","unstructured":"Jiajun Xu Zhiyuan Li Wei Chen Qun Wang Xin Gao Qi Cai and Ziyuan Ling. 2024. On-Device Language Models: A Comprehensive Review. arXiv:2409.00088 [cs.CL] https:\/\/arxiv.org\/abs\/2409.00088"},{"key":"e_1_3_2_1_20_1","unstructured":"Chao Yi Dian Chen Gaoyang Guo Jiakai Tang Jian Wu Jing Yu Mao Zhang Sunhao Dai Wen Chen Wenjun Yang Yuning Jiang Zhujin Gao Bo Zheng Chi Li Dimin Wang Dixuan Wang Fan Li Fan Zhang Haibin Chen Haozhuang Liu Jialin Zhu Jiamang Wang Jiawei Wu Jin Cui Ju Huang Kai Zhang Kan Liu Lang Tian Liang Rao Longbin Li Lulu Zhao Na He Peiyang Wang Qiqi Huang Tao Luo Wenbo Su Xiaoxiao He Xin Tong Xu Chen Xunke Xi Yang Li Yaxuan Wu Yeqiu Yang Yi Hu Yinnan Song Yuchen Li Yujie Luo Yujin Yuan Yuliang Yan Zhengyang Wang Zhibo Xiao Zhixin Ma Zile Zhou and Ziqi Zhang. 2025. RecGPT Technical Report. arXiv:2507.22879 [cs.IR] https:\/\/arxiv.org\/abs\/2507.22879"},{"key":"e_1_3_2_1_21_1","volume-title":"On-device recommender systems: A comprehensive survey. Data Science and Engineering","author":"Yin Hongzhi","year":"2025","unstructured":"Hongzhi Yin, Liang Qu, Tong Chen, Wei Yuan, Ruiqi Zheng, Jing Long, Xin Xia, Yuhui Shi, and Chengqi Zhang. 2025. On-device recommender systems: A comprehensive survey. Data Science and Engineering (2025), 1-30."},{"key":"e_1_3_2_1_22_1","unstructured":"Yipeng Yu. 2026. Deep Research of Deep Research: From Transformer to Agent From AI to AI for Science. arXiv:2603.28361 [cs.AI] https:\/\/arxiv.org\/abs\/2603.28361"},{"key":"e_1_3_2_1_23_1","unstructured":"Jiaqi Zhai Lucy Liao Xing Liu YuemingWang Rui Li Xuan Cao Leon Gao Zhaojie Gong Fangda Gu Michael He et al. 2024. Actions speak louder than words: Trillion-parameter sequential transducers for generative recommendations. arXiv preprint arXiv:2402.17152 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:17:30Z","timestamp":1784135850000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808410"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":24,"alternative-id":["10.1145\/3805712.3808410","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808410","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}