{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:38Z","timestamp":1786120838965,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":41,"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\/3770855.3818494","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"7489-7500","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TokenMixer-Large: Scaling Up Large Ranking Models in Industrial Recommenders"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4311-5374","authenticated-orcid":false,"given":"Yuchen","family":"Jiang","sequence":"first","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4167-5245","authenticated-orcid":false,"given":"Jie","family":"Zhu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1432-5095","authenticated-orcid":false,"given":"Xintian","family":"Han","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Hangzhou, 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 Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9283-1064","authenticated-orcid":false,"given":"Kunmin","family":"Bai","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2114-671X","authenticated-orcid":false,"given":"Mingyu","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7553-4944","authenticated-orcid":false,"given":"Shikang","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8233-3063","authenticated-orcid":false,"given":"Ruihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0655-4317","authenticated-orcid":false,"given":"Wenlin","family":"Zhao","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7473-3837","authenticated-orcid":false,"given":"Shipeng","family":"Bai","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9841-8820","authenticated-orcid":false,"given":"Sijin","family":"Zhou","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0201-1861","authenticated-orcid":false,"given":"Huizhi","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance Inc., 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 Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7401-7195","authenticated-orcid":false,"given":"Wenda","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3331-4065","authenticated-orcid":false,"given":"Ziyan","family":"Gong","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1680-4687","authenticated-orcid":false,"given":"Haoran","family":"Ding","sequence":"additional","affiliation":[{"name":"ByteDance Inc., 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 Inc., Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9329-2891","authenticated-orcid":false,"given":"Deping","family":"Xie","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2716-9885","authenticated-orcid":false,"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Inc., 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 Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2580-0983","authenticated-orcid":false,"given":"Peng","family":"Xu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, CA, USA"}],"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":"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","first-page":"1352","article-title":"Rezero is all you need: Fast convergence at large depth. In Uncertainty in Artificial Intelligence","author":"Bachlechner Thomas","year":"2021","unstructured":"Thomas Bachlechner, Bodhisattwa Prasad Majumder, Henry Mao, Gary Cottrell, and Julian McAuley. 2021. Rezero is all you need: Fast convergence at large depth. In Uncertainty in Artificial Intelligence. PMLR, 1352-1361.","journal-title":"PMLR"},{"key":"e_1_3_2_1_3_1","volume-title":"LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders. arXiv:2505.04421 [cs.IR] https:\/\/arxiv.org\/abs\/2505.04421","author":"Chai Zheng","year":"2025","unstructured":"Zheng Chai, Qin Ren, Xijun Xiao, Huizhi Yang, Bo Han, Sijun Zhang, Di Chen, Hui Lu, Wenlin Zhao, Lele Yu, Xionghang Xie, Shiru Ren, Xiang Sun, Yaocheng Tan, Peng Xu, Yuchao Zheng, and Di Wu. 2025. LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenders. arXiv:2505.04421 [cs.IR] https:\/\/arxiv.org\/abs\/2505.04421"},{"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","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341261"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_7_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research 24, 240 (2023), 1-113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_9_1","volume-title":"Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models. arXiv preprint arXiv:2401.06066","author":"Dai Damai","year":"2024","unstructured":"Damai Dai, Chengqi Deng, Chenggang Zhao, RX Xu, Huazuo Gao, Deli Chen, Jiashi Li, Wangding Zeng, Xingkai Yu, Yu Wu, et al. 2024. Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models. arXiv preprint arXiv:2401.06066 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research 23, 120 (2022), 1-39.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_12_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_13_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_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761565"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557137"},{"key":"e_1_3_2_1_16_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_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_2_1_18_1","unstructured":"Jianghao Lin Xinyi Dai Yunjia Xi Weiwen Liu Bo Chen Hao Zhang Yong Liu Chuhan Wu Xiangyang Li Chenxu Zhu et al. 2023. How can recommender systems benefit from large language models: A survey. ACM Transactions on Information Systems (2023)."},{"key":"e_1_3_2_1_19_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu 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_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412744"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3233770"},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. Pmlr, 8821-8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International conference on machine learning. Pmlr, 8821-8831."},{"key":"e_1_3_2_1_24_1","volume-title":"Learning representations by back-propagating errors. nature 323, 6088","author":"Rumelhart David E","year":"1986","unstructured":"David E Rumelhart, Geoffrey E Hinton, and Ronald J Williams. 1986. Learning representations by back-propagating errors. nature 323, 6088 (1986), 533-536."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2560534"},{"key":"e_1_3_2_1_27_1","volume-title":"Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems 34","author":"Tolstikhin Ilya O","year":"2021","unstructured":"Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, et al. 2021. Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems 34 (2021), 24261-24272."},{"key":"e_1_3_2_1_28_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450078"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.14711"},{"key":"e_1_3_2_1_33_1","volume-title":"Performance Law of Large Language Models. arXiv preprint arXiv:2408.09895","author":"Wu Chuhan","year":"2024","unstructured":"Chuhan Wu and Ruiming Tang. 2024. Performance Law of Large Language Models. arXiv preprint arXiv:2408.09895 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction. arXiv preprint arXiv:2511.12081","author":"Yan Bencheng","year":"2025","unstructured":"Bencheng Yan, Yuejie Lei, Zhiyuan Zeng, Di Wang, Kaiyi Lin, Pengjie Wang, Jian Xu, and Bo Zheng. 2025. From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction. arXiv preprint arXiv:2511.12081 (2025)."},{"key":"e_1_3_2_1_35_1","volume-title":"Forty-first International Conference on Machine Learning.","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 Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_36_1","volume-title":"Forty-first International Conference on Machine Learning.","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. 2024. Wukong: Towards a Scaling Law for Large-Scale Recommendation. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_37_1","volume-title":"DHEN: A deep and hierarchical ensemble network for large-scale click-through rate prediction. arXiv preprint arXiv:2203.11014","author":"Zhang Buyun","year":"2022","unstructured":"Buyun Zhang, Liang Luo, Xi Liu, Jay Li, Zeliang Chen, Weilin Zhang, Xiaohan Wei, Yuchen Hao, Michael Tsang, Wenjun Wang, et al. 2022. DHEN: A deep and hierarchical ensemble network for large-scale click-through rate prediction. arXiv preprint arXiv:2203.11014 (2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"Root mean square layer normalization. Advances in neural information processing systems 32","author":"Zhang Biao","year":"2019","unstructured":"Biao Zhang and Rico Sennrich. 2019. Root mean square layer normalization. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761507"},{"key":"e_1_3_2_1_41_1","volume-title":"St-moe: Designing stable and transferable sparse expert models. arXiv preprint arXiv:2202.08906","author":"Zoph Barret","year":"2022","unstructured":"Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus. 2022. St-moe: Designing stable and transferable sparse expert models. arXiv preprint arXiv:2202.08906 (2022)."}],"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":"2026-08-07T01:14:51Z","timestamp":1786065291000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":41,"alternative-id":["10.1145\/3770855.3818494","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818494","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"}}]}}