{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:29:44Z","timestamp":1765499384203,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761015","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:59:18Z","timestamp":1762559958000},"page":"2022-2031","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MARM: Unlocking the Recommendation Cache Scaling-Law through Memory Augmentation and Scalable Complexity"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3393-4438","authenticated-orcid":false,"given":"Xiao","family":"Lv","sequence":"first","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2681-0119","authenticated-orcid":false,"given":"Jiangxia","family":"Cao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5371-1822","authenticated-orcid":false,"given":"Shijie","family":"Guan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0204-1471","authenticated-orcid":false,"given":"Xiaoyou","family":"Zhou","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0857-5523","authenticated-orcid":false,"given":"Zhiguang","family":"Qi","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1570-5184","authenticated-orcid":false,"given":"Yaqiang","family":"Zang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1329-3876","authenticated-orcid":false,"given":"Ben","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8550-279X","authenticated-orcid":false,"given":"Guorui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Gqa: Training generalized multi-query transformer models from multi-head checkpoints. arXiv preprint arXiv:2305.13245","author":"Ainslie Joshua","year":"2023","unstructured":"Joshua Ainslie, James Lee-Thorp, Michiel de Jong, Yury Zemlyanskiy, Federico Lebr\u00f3n, and Sumit Sanghai. 2023. Gqa: Training generalized multi-query transformer models from multi-head checkpoints. arXiv preprint arXiv:2305.13245 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557082"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599922"},{"key":"e_1_3_2_1_5_1","volume-title":"End-to-end user behavior retrieval in click-through rateprediction model. arXiv preprint arXiv:2108.04468","author":"Chen Qiwei","year":"2021","unstructured":"Qiwei Chen, Changhua Pei, Shanshan Lv, Chao Li, Junfeng Ge, and Wenwu Ou. 2021. End-to-end user behavior retrieval in click-through rateprediction model. arXiv preprint arXiv:2108.04468 (2021)."},{"key":"e_1_3_2_1_6_1","volume-title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference. arXiv preprint arXiv:2402.09398","author":"Dong Harry","year":"2024","unstructured":"Harry Dong, Xinyu Yang, Zhenyu Zhang, Zhangyang Wang, Yuejie Chi, and Beidi Chen. 2024. Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference. arXiv preprint arXiv:2402.09398 (2024)."},{"key":"e_1_3_2_1_7_1","unstructured":"Daya Guo Qihao Zhu Dejian Yang Zhenda Xie Kai Dong Wentao Zhang Guanting Chen Xiao Bi Yu Wu YK Li et al. 2024. DeepSeek-Coder: When the Large Language Model Meets Programming-The Rise of Code Intelligence. arXiv preprint arXiv:2401.14196 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Hydragen: High-Throughput LLM Inference with Shared Prefixes. arXiv preprint arXiv:2402.05099","author":"Juravsky Jordan","year":"2024","unstructured":"Jordan Juravsky, Bradley Brown, Ryan Ehrlich, Daniel Y Fu, Christopher R\u00e9, and Azalia Mirhoseini. 2024. Hydragen: High-Throughput LLM Inference with Shared Prefixes. arXiv preprint arXiv:2402.05099 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330666"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412744"},{"key":"e_1_3_2_1_12_1","volume-title":"Fast transformer decoding: One write-head is all you need. arXiv preprint arXiv:1911.02150","author":"Shazeer Noam","year":"2019","unstructured":"Noam Shazeer. 2019. Fast transformer decoding: One write-head is all you need. arXiv preprint arXiv:1911.02150 (2019)."},{"key":"e_1_3_2_1_13_1","unstructured":"Zihua Si Lin Guan ZhongXiang Sun Xiaoxue Zang Jing Lu Yiqun Hui Xingchao Cao Zeyu Yang Yichen Zheng Dewei Leng et al. 2024. TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou. arXiv preprint arXiv:2407.16357 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_15_1","volume-title":"Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453 (2023)."},{"key":"e_1_3_2_1_16_1","unstructured":"Zihao Ye Lequn Chen Ruihang Lai Yilong Zhao Size Zheng Junru Shao Bohan Hou Hongyi Jin Yifei Zuo Liangsheng Yin Tianqi Chen and Luis Ceze. 2024. Accelerating Self-Attentions for LLM Serving with FlashInfer. https:\/\/flashinfer.ai\/2024\/02\/02\/introduce-flashinfer.html"},{"key":"e_1_3_2_1_17_1","volume-title":"SubGen: Token Generation in Sublinear Time and Memory. arXiv preprint arXiv:2402.06082","author":"Zandieh Amir","year":"2024","unstructured":"Amir Zandieh, Insu Han, Vahab Mirrokni, and Amin Karbasi. 2024. SubGen: Token Generation in Sublinear Time and Memory. arXiv preprint arXiv:2402.06082 (2024)."},{"key":"e_1_3_2_1_18_1","unstructured":"Jiaqi Zhai Lucy Liao Xing Liu Yueming Wang 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_19_1","volume-title":"Wukong: Towards a Scaling Law for Large-Scale Recommendation. arXiv preprint arXiv:2403.02545","author":"Zhang Buyun","year":"2024","unstructured":"Buyun Zhang, Liang Luo, Yuxin Chen, Jade Nie, Xi Liu, Daifeng Guo, Yanli Zhao, Shen Li, Yuchen Hao, Yantao Yao, et al., 2024a. Wukong: Towards a Scaling Law for Large-Scale Recommendation. arXiv preprint arXiv:2403.02545 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531829"},{"key":"e_1_3_2_1_21_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zhang Zhenyu","year":"2024","unstructured":"Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher R\u00e9, Clark Barrett, et al., 2024b. H2o: Heavy-hitter oracle for efficient generative inference of large language models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:24:55Z","timestamp":1765499095000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761015"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":23,"alternative-id":["10.1145\/3746252.3761015","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761015","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}