{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:44Z","timestamp":1786120844759,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"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":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818451","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"8258-8266","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MSN: A Memory-based Sparse Activation Scaling Framework for Large-scale Industrial Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7553-4944","authenticated-orcid":false,"given":"Shikang","family":"Wu","sequence":"first","affiliation":[{"name":"ByteDance Search, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5133-4452","authenticated-orcid":false,"given":"Hui","family":"Lu","sequence":"additional","affiliation":[{"name":"ByteDance AML, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2568-4637","authenticated-orcid":false,"given":"Jinqiu","family":"Jin","sequence":"additional","affiliation":[{"name":"ByteDance Search, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9823-2990","authenticated-orcid":false,"given":"Zheng","family":"Chai","sequence":"additional","affiliation":[{"name":"ByteDance AML, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4172-6740","authenticated-orcid":false,"given":"Shiyong","family":"Hong","sequence":"additional","affiliation":[{"name":"ByteDance Search, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8864-915X","authenticated-orcid":false,"given":"Junjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Search, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7795-0579","authenticated-orcid":false,"given":"Shanlei","family":"Mu","sequence":"additional","affiliation":[{"name":"ByteDance Search, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0297-5348","authenticated-orcid":false,"given":"Kaiyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"ByteDance AML, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9781-4435","authenticated-orcid":false,"given":"Tianyi","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance AML, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9804-2721","authenticated-orcid":false,"given":"Yuchao","family":"Zheng","sequence":"additional","affiliation":[{"name":"ByteDance AML, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0959-2714","authenticated-orcid":false,"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Search, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6403-4176","authenticated-orcid":false,"given":"Jingjian","family":"Lin","sequence":"additional","affiliation":[{"name":"ByteDance Search, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_2_1","unstructured":"Vincent-Pierre Berges Barlas Oguz Daniel HAZIZA Wen-tau Yih Luke Zettlemoyer and Gargi Ghosh. 2025. Memory Layers at Scale. In ICML."},{"key":"e_1_3_2_1_3_1","volume-title":"NeurIPS","volume":"29","author":"Blondel Mathieu","year":"2016","unstructured":"Mathieu Blondel, Akinori Fujino, Naonori Ueda, and Masakazu Ishihata. 2016. Higher-order factorization machines. NeurIPS, Vol. 29 (2016)."},{"key":"e_1_3_2_1_4_1","first-page":"4234","article-title":"Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders","author":"Chai Zheng","year":"2025","unstructured":"Zheng Chai, Hui Lu, Di Chen, Qin Ren, Yuchao Zheng, and Xun Zhou. 2025. Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders. In SIGIR. 4234-4238.","journal-title":"SIGIR."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_6_1","volume-title":"Scalable Lookup: A New Axis of Sparsity for Large Language Models. arXiv preprint arXiv:2601.07372","author":"Cheng Xin","year":"2026","unstructured":"Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Yukun Li, et al., 2026. Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models. arXiv preprint arXiv:2601.07372 (2026)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_8_1","volume-title":"H Chi","author":"Gui Huan","year":"2023","unstructured":"Huan Gui, Ruoxi Wang, Ke Yin, Long Jin, Maciej Kula, Taibai Xu, Lichan Hong, and Ed H Chi. 2023. Hiformer: Heterogeneous feature interactions learning with transformers for recommender systems. arXiv preprint arXiv:2311.05884 (2023)."},{"key":"e_1_3_2_1_9_1","first-page":"1725","article-title":"DeepFM: a factorization-machine based neural network for CTR prediction","author":"Guo Huifeng","year":"2017","unstructured":"Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. In IJCAI. 1725-1731.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_10_1","first-page":"16891","article-title":"On the Embedding Collapse when Scaling up Recommendation Models","author":"Guo Xingzhuo","year":"2024","unstructured":"Xingzhuo Guo, Junwei Pan, Ximei Wang, Baixu Chen, Jie Jiang, and Mingsheng Long. 2024. On the Embedding Collapse when Scaling up Recommendation Models. In ICML. PMLR, 16891-16909.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_11_1","first-page":"5731","article-title":"Mtgr: Industrial-scale generative recommendation framework in meituan","author":"Han Ruidong","year":"2025","unstructured":"Ruidong Han, Bin Yin, Shangyu Chen, He Jiang, Fei Jiang, Xiang Li, Chi Ma, Mincong Huang, Xiaoguang Li, Chunzhen Jing, et al., 2025b. Mtgr: Industrial-scale generative recommendation framework in meituan. In CIKM. 5731-5738.","journal-title":"CIKM."},{"key":"e_1_3_2_1_12_1","volume-title":"LEMUR: Large scale End-to-end MUltimodal Recommendation. arXiv preprint arXiv:2511.10962","author":"Han Xintian","year":"2025","unstructured":"Xintian Han, Honggang Chen, Quan Lin, Jingyue Gao, Xiangyuan Ren, Lifei Zhu, Zhisheng Ye, Shikang Wu, XiongHang Xie, Xiaochu Gan, et al., 2025a. LEMUR: Large scale End-to-end MUltimodal Recommendation. arXiv preprint arXiv:2511.10962 (2025)."},{"key":"e_1_3_2_1_13_1","first-page":"355","article-title":"Neural factorization machines for sparse predictive analytics","author":"He Xiangnan","year":"2017","unstructured":"Xiangnan He and Tat-Seng Chua. 2017. Neural factorization machines for sparse predictive analytics. In SIGIR. 355-364.","journal-title":"SIGIR."},{"key":"e_1_3_2_1_14_1","volume-title":"Mixture of a million experts. arXiv preprint arXiv:2407.04153","author":"Xu Owen He.","year":"2024","unstructured":"Xu Owen He. 2024. Mixture of a million experts. arXiv preprint arXiv:2407.04153 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Yunwen Huang Shiyong Hong Xijun Xiao Jinqiu Jin Xuanyuan Luo Zhe Wang Zheng Chai Shikang Wu Yuchao Zheng and Jingjian Lin. 2026 b. HyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Prediction. In SIGIR.","DOI":"10.1145\/3805712.3809745"},{"key":"e_1_3_2_1_16_1","unstructured":"Zihao Huang Yu Bao Qiyang Min Siyan Chen Ran Guo Hongzhi Huang Defa Zhu Yutao Zeng Banggu Wu Xun Zhou et al. 2026 a. Ultramemv2: Memory networks scaling to 120b parameters with superior long-context learning. In ICLR."},{"key":"e_1_3_2_1_17_1","unstructured":"Zihao Huang Qiyang Min Hongzhi Huang Yutao Zeng Defa Zhu Ran Guo et al. 2025. Ultra-Sparse Memory Network. In ICLR."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3705328.3748046"},{"key":"e_1_3_2_1_19_1","volume-title":"NeurIPS","volume":"32","author":"Lample Guillaume","year":"2019","unstructured":"Guillaume Lample, Alexandre Sablayrolles, Marc'Aurelio Ranzato, Ludovic Denoyer, and Herv\u00e9 J\u00e9gou. 2019. Large memory layers with product keys. NeurIPS, Vol. 32 (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"Wei Li, Hongwei Li, Jie Hua, Yiqi Chen, Zhao Zhu, Rui Jian, Xuan Cao, Bi Xue, et al.","author":"Li Dai","year":"2025","unstructured":"Dai Li, Kevin Course, Wei Li, Hongwei Li, Jie Hua, Yiqi Chen, Zhao Zhu, Rui Jian, Xuan Cao, Bi Xue, et al., 2025. Realizing Scaling Laws in Recommender Systems: A Foundation-Expert Paradigm for Hyperscale Model Deployment. arXiv preprint arXiv:2508.02929 (2025)."},{"key":"e_1_3_2_1_21_1","first-page":"539","article-title":"Fi-gnn: Modeling feature interactions via graph neural networks for ctr prediction","author":"Li Zekun","year":"2019","unstructured":"Zekun Li, Zeyu Cui, Shu Wu, Xiaoyu Zhang, and Liang Wang. 2019. Fi-gnn: Modeling feature interactions via graph neural networks for ctr prediction. In CIKM. 539-548.","journal-title":"CIKM."},{"key":"e_1_3_2_1_22_1","first-page":"1754","article-title":"xdeepfm: Combining explicit and implicit feature interactions for recommender systems","author":"Lian Jianxun","year":"2018","unstructured":"Jianxun Lian, Xiaohuan Zhou, Fuzheng Zhang, Zhongxia Chen, Xing Xie, and Guangzhong Sun. 2018. xdeepfm: Combining explicit and implicit feature interactions for recommender systems. In KDD. 1754-1763.","journal-title":"KDD."},{"key":"e_1_3_2_1_23_1","first-page":"2022","article-title":"MARM: Unlocking the Recommendation Cache Scaling-Law through Memory Augmentation and Scalable Complexity","author":"Lv Xiao","year":"2025","unstructured":"Xiao Lv, Jiangxia Cao, Shijie Guan, Xiaoyou Zhou, Zhiguang Qi, Yaqiang Zang, Ben Wang, and Guorui Zhou. 2025. MARM: Unlocking the Recommendation Cache Scaling-Law through Memory Augmentation and Scalable Complexity. In CIKM. 2022-2031.","journal-title":"CIKM."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25577"},{"key":"e_1_3_2_1_25_1","volume-title":"MDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation through Tokenization. In KDD.","author":"Mu Shanlei","year":"2026","unstructured":"Shanlei Mu, Yuchen Jiang, Shikang Wu, Shiyong Hong, Tianmu Sha, Junjie Zhang, Jie Zhu, Zhe Chen, Zhe Wang, and Jingjian Lin. 2026. MDL: A Unified Multi-Distribution Learner in Large-scale Industrial Recommendation through Tokenization. In KDD."},{"key":"e_1_3_2_1_26_1","first-page":"5566","article-title":"Ads recommendation in a collapsed and entangled world","author":"Pan Junwei","year":"2024","unstructured":"Junwei Pan, Wei Xue, Ximei Wang, Haibin Yu, Xun Liu, Shijie Quan, Xueming Qiu, Dapeng Liu, Lei Xiao, and Jie Jiang. 2024. Ads recommendation in a collapsed and entangled world. In KDD. 5566-5577.","journal-title":"KDD."},{"key":"e_1_3_2_1_27_1","volume-title":"MTmixAtt: Integrating Mixture-of-Experts with Multi-Mix Attention for Large-Scale Recommendation. arXiv preprint arXiv:2510.15286","author":"Qi Xianyang","year":"2025","unstructured":"Xianyang Qi, Yuan Tian, Zhaoyu Hu, Zhirui Kuai, Chang Liu, Hongxiang Lin, and Lei Wang. 2025. MTmixAtt: Integrating Mixture-of-Experts with Multi-Mix Attention for Large-Scale Recommendation. arXiv preprint arXiv:2510.15286 (2025)."},{"key":"e_1_3_2_1_28_1","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme Carlos","year":"2021","unstructured":"Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, Andr\u00e9 Susano Pinto, Daniel Keysers, and Neil Houlsby. 2021. Scaling vision with sparse mixture of experts. NeurIPS, Vol. 34 (2021), 8583-8595.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_29_1","volume-title":"STEM: Scaling Transformers with Embedding Modules. In ICLR.","author":"Sadhukhan Ranajoy","year":"2026","unstructured":"Ranajoy Sadhukhan, Sheng Cao, Harry Dong, Changsheng Zhao, Attiano Purpura-Pontoniere, Yuandong Tian, Zechun Liu, and Beidi Chen. 2026. STEM: Scaling Transformers with Embedding Modules. In ICLR."},{"key":"e_1_3_2_1_30_1","first-page":"255","article-title":"Deep crossing: Web-scale modeling without manually crafted combinatorial features","author":"Shan Ying","year":"2016","unstructured":"Ying Shan, T Ryan Hoens, Jian Jiao, Haijing Wang, Dong Yu, and JC Mao. 2016. Deep crossing: Web-scale modeling without manually crafted combinatorial features. In KDD. 255-262.","journal-title":"KDD."},{"key":"e_1_3_2_1_31_1","volume-title":"Wei Guo, Yong Liu, Huifeng Guo, Defu Lian, Ruiming Tang, and Enhong Chen.","author":"Shen Tingjia","year":"2024","unstructured":"Tingjia Shen, Hao Wang, Chuhan Wu, Jin Yao Chin, Wei Guo, Yong Liu, Huifeng Guo, Defu Lian, Ruiming Tang, and Enhong Chen. 2024. Optimizing sequential recommendation models with scaling laws and approximate entropy. arXiv preprint arXiv:2412.00430 (2024)."},{"key":"e_1_3_2_1_32_1","first-page":"1161","article-title":"Autoint: Automatic feature interaction learning via self-attentive neural networks","author":"Song Weiping","year":"2019","unstructured":"Weiping Song, Chence Shi, Zhiping Xiao, Zhijian Duan, Yewen Xu, Ming Zhang, and Jian Tang. 2019. Autoint: Automatic feature interaction learning via self-attentive neural networks. In CIKM. 1161-1170.","journal-title":"CIKM."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"e_1_3_2_1_34_1","first-page":"2893","article-title":"Scaling transformers for discriminative recommendation via generative pretraining","author":"Wang Chunqi","year":"2025","unstructured":"Chunqi Wang, Bingchao Wu, Zheng Chen, Lei Shen, Bing Wang, and Xiaoyi Zeng. 2025. Scaling transformers for discriminative recommendation via generative pretraining. In KDD. 2893-2903.","journal-title":"KDD."},{"key":"e_1_3_2_1_35_1","first-page":"1","article-title":"Deep & cross network for ad click predictions","author":"Wang Ruoxi","year":"2017","unstructured":"Ruoxi Wang, Bin Fu, Gang Fu, and Mingliang Wang. 2017. Deep & cross network for ad click predictions. In ADKDD. 1-7.","journal-title":"ADKDD."},{"key":"e_1_3_2_1_36_1","first-page":"1785","article-title":"Dcn v2: Improved deep & cross network and practical lessons for web-scale learning to rank systems","author":"Wang Ruoxi","year":"2021","unstructured":"Ruoxi Wang, Rakesh Shivanna, Derek Cheng, Sagar Jain, Dong Lin, Lichan Hong, and Ed Chi. 2021. Dcn v2: Improved deep & cross network and practical lessons for web-scale learning to rank systems. In WWW. 1785-1797.","journal-title":"WWW."},{"key":"e_1_3_2_1_37_1","first-page":"74530","article-title":"Augmenting language models with long-term memory","volume":"36","author":"Wang Weizhi","year":"2023","unstructured":"Weizhi Wang, Li Dong, Hao Cheng, Xiaodong Liu, Xifeng Yan, Jianfeng Gao, and Furu Wei. 2023. Augmenting language models with long-term memory. NeurIPS, Vol. 36 (2023), 74530-74543.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_38_1","first-page":"58484","article-title":"Actions Speak Louder than Words","author":"Zhai Jiaqi","year":"2024","unstructured":"Jiaqi Zhai, Lucy Liao, Xing Liu, Yueming Wang, Rui Li, Xuan Cao, Leon Gao, Zhaojie Gong, Fangda Gu, Jiayuan He, et al., 2024. Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations. In ICML. PMLR, 58484-58509.","journal-title":"Trillion-Parameter Sequential Transducers for Generative Recommendations. In ICML. PMLR"},{"key":"e_1_3_2_1_39_1","first-page":"59421","article-title":"Wukong: Towards a Scaling Law for Large-Scale Recommendation","author":"Zhang Buyun","year":"2024","unstructured":"Buyun Zhang, Liang Luo, Yuxin Chen, Jade Nie, Xi Liu, Shen Li, Yanli Zhao, Yuchen Hao, Yantao Yao, Ellie Dingqiao Wen, et al., 2024a. Wukong: Towards a Scaling Law for Large-Scale Recommendation. In ICML. PMLR, 59421-59434.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_40_1","first-page":"1189","article-title":"Deep pattern network for click-through rate prediction","author":"Zhang Hengyu","year":"2024","unstructured":"Hengyu Zhang, Junwei Pan, Dapeng Liu, Jie Jiang, and Xiu Li. 2024b. Deep pattern network for click-through rate prediction. In SIGIR. 1189-1199.","journal-title":"SIGIR."},{"key":"e_1_3_2_1_41_1","first-page":"1","article-title":"Parallel top-k algorithms on gpu: A comprehensive study and new methods","author":"Zhang Jingrong","year":"2023","unstructured":"Jingrong Zhang, Akira Naruse, Xipeng Li, and Yong Wang. 2023. Parallel top-k algorithms on gpu: A comprehensive study and new methods. In SC. 1-13.","journal-title":"SC."},{"key":"e_1_3_2_1_42_1","first-page":"1","volume-title":"CSUR","volume":"52","author":"Zhang Shuai","year":"2019","unstructured":"Shuai Zhang, Lina Yao, Aixin Sun, and Yi Tay. 2019. Deep learning based recommender system: A survey and new perspectives. CSUR, Vol. 52, 1 (2019), 1-38."},{"key":"e_1_3_2_1_43_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 Vol. 1 2 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29946"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"},{"key":"e_1_3_2_1_46_1","first-page":"1059","article-title":"Deep interest network for click-through rate prediction","author":"Zhou Guorui","year":"2018","unstructured":"Guorui Zhou, Xiaoqiang Zhu, Chenru Song, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, and Kun Gai. 2018. Deep interest network for click-through rate prediction. In KDD. 1059-1068.","journal-title":"KDD."},{"key":"e_1_3_2_1_47_1","first-page":"413","article-title":"Temporal Interest Network for User Response Prediction","author":"Zhou Haolin","year":"2024","unstructured":"Haolin Zhou, Junwei Pan, Xinyi Zhou, Xihua Chen, Jie Jiang, Xiaofeng Gao, and Guihai Chen. 2024. Temporal Interest Network for User Response Prediction. In WWW. 413-422.","journal-title":"WWW."},{"key":"e_1_3_2_1_48_1","first-page":"6309","article-title":"Rankmixer: Scaling up ranking models in industrial recommenders","author":"Zhu Jie","year":"2025","unstructured":"Jie Zhu, Zhifang Fan, Xiaoxie Zhu, Yuchen Jiang, Hangyu Wang, Xintian Han, Haoran Ding, Xinmin Wang, Wenlin Zhao, Zhen Gong, et al., 2025a. Rankmixer: Scaling up ranking models in industrial recommenders. In CIKM. 6309-6316.","journal-title":"CIKM."},{"key":"e_1_3_2_1_49_1","first-page":"22968","article-title":"Addressing representation collapse in vector quantized models with one linear layer","author":"Zhu Yongxin","year":"2025","unstructured":"Yongxin Zhu, Bocheng Li, Yifei Xin, Zhihua Xia, and Linli Xu. 2025b. Addressing representation collapse in vector quantized models with one linear layer. In ICCV. 22968-22977.","journal-title":"ICCV."}],"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.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:31:25Z","timestamp":1786066285000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818451"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":49,"alternative-id":["10.1145\/3770855.3818451","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818451","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}