{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:11Z","timestamp":1786120811020,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":48,"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-nc-nd\/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\/3770855.3818505","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:43Z","timestamp":1786036543000},"page":"8389-8398","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Unity: Fully Self-Supervised Pretraining with Transformers for Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1607-7446","authenticated-orcid":false,"given":"Shuang","family":"Yang","sequence":"first","affiliation":[{"name":"Meta AI Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5814-1170","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Meta AI Research, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7879-5315","authenticated-orcid":false,"given":"Tao","family":"Liu","sequence":"additional","affiliation":[{"name":"Meta AI Research, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3057-6450","authenticated-orcid":false,"given":"Feng","family":"Qi","sequence":"additional","affiliation":[{"name":"Meta AI Research, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4718-6792","authenticated-orcid":false,"given":"Kaushik","family":"Rangadurai","sequence":"additional","affiliation":[{"name":"Meta AI Research, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4560-6361","authenticated-orcid":false,"given":"Luke","family":"Simon","sequence":"additional","affiliation":[{"name":"Meta AI Research, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6126-2564","authenticated-orcid":false,"given":"Sandeep","family":"Pandey","sequence":"additional","affiliation":[{"name":"Meta AI Research, Sunnyvale, 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","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557029"},{"key":"e_1_3_2_1_3_1","unstructured":"Mido Assran Adrien Bardes David Fan Quentin Garrido Russell Howes Mojtaba Komeili Matthew Muckley Ammar Rizvi Claire Roberts Koustuv Sinha Artem Zholus Sergio Arnaud Abha Gejji Ada Martin Francois Robert Hogan Daniel Dugas Piotr Bojanowski Vasil Khalidov Patrick Labatut Francisco Massa Marc Szafraniec Kapil Krishnakumar Yong Li Xiaodong Ma Sarath Chandar Franziska Meier Yann LeCun Michael Rabbat and Nicolas Ballas. 2025. V-JEPA 2: Self-Supervised Video Models Enable Understanding Prediction and Planning. arXiv:2506.09985 [cs.AI] https:\/\/arxiv.org\/abs\/2506.09985"},{"key":"e_1_3_2_1_4_1","volume-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. CoRR abs\/2006.11477","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. CoRR abs\/2006.11477 (2020). arXiv:2006.11477 https:\/\/arxiv.org\/abs\/2006. 11477"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482246"},{"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","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_8_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR abs\/1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR abs\/1810.04805 (2018). arXiv:1810.04805 http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_2_1_9_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 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_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481953"},{"key":"e_1_3_2_1_11_1","volume-title":"Deepfm: An end-to-end wide & deep learning framework for CTR prediction. arXiv preprint arXiv:1804.04950","author":"Guo Huifeng","year":"2018","unstructured":"Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, Xiuqiang He, and Zhenhua Dong. 2018. Deepfm: An end-to-end wide & deep learning framework for CTR prediction. arXiv preprint arXiv:1804.04950 (2018)."},{"key":"e_1_3_2_1_12_1","volume-title":"Girshick","author":"He Kaiming","year":"2021","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross B. Girshick. 2021. Masked Autoencoders Are Scalable Vision Learners. CoRR abs\/2111.06377 (2021). arXiv:2111.06377 https:\/\/arxiv.org\/abs\/2111.06377"},{"key":"e_1_3_2_1_13_1","unstructured":"Xiangnan He and Tat-Seng Chua. 2017. Neural Factorization Machines for Sparse Predictive Analytics. arXiv:1708.05027 [cs.LG] https:\/\/arxiv.org\/abs\/1708.05027"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_3_2_1_15_1","unstructured":"Sukjun Hwang Brandon Wang and Albert Gu. 2025. Dynamic Chunking for End-to-End Hierarchical Sequence Modeling. arXiv:2507.07955 [cs.LG] https: \/\/arxiv.org\/abs\/2507.07955"},{"key":"e_1_3_2_1_16_1","volume-title":"Product quantization for nearest neighbor search","author":"Jegou Herve","year":"2010","unstructured":"Herve Jegou, Matthijs Douze, and Cordelia Schmid. 2010. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence 33, 1 (2010), 117-128."},{"key":"e_1_3_2_1_17_1","first-page":"597","volume-title":"ICASSP'82","volume":"7","author":"Juang Biing-Hwang","year":"1982","unstructured":"Biing-Hwang Juang and A Gray. 1982. Multiple stage vector quantization for speech coding. In ICASSP'82. IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 7. IEEE, 597-600."},{"key":"e_1_3_2_1_18_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_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_1_20_1","unstructured":"Yann LeCun. 2022. A Path Towards Autonomous Machine Intelligence Version. (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350950"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5346"},{"key":"e_1_3_2_1_23_1","volume-title":"Stacked quantizers for compositional vector compression. arXiv preprint arXiv:1411.2173","author":"Martinez Julieta","year":"2014","unstructured":"Julieta Martinez, Holger H Hoos, and James J Little. 2014. Stacked quantizers for compositional vector compression. arXiv preprint arXiv:1411.2173 (2014)."},{"key":"e_1_3_2_1_24_1","volume-title":"Finite scalar quantization: Vq-vae made simple. arXiv preprint arXiv:2309.15505","author":"Mentzer Fabian","year":"2023","unstructured":"Fabian Mentzer, David Minnen, Eirikur Agustsson, and Michael Tschannen. 2023. Finite scalar quantization: Vq-vae made simple. arXiv preprint arXiv:2309.15505 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3533727"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492900002919"},{"key":"e_1_3_2_1_27_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. CoRR abs\/2103.00020 (2021). arXiv:2103.00020 https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_2_1_28_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. OpenAI Technical Report (2018)."},{"key":"e_1_3_2_1_29_1","volume-title":"Chi, and Maheswaran Sathiamoorthy","author":"Rajput Shashank","year":"2023","unstructured":"Shashank Rajput, Nikhil Mehta, Anima Singh, Raghunandan H. Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Q. Tran, Jonah Samost, Maciej Kula, Ed H. Chi, and Maheswaran Sathiamoorthy. 2023. Recommender Systems with Generative Retrieval. arXiv:2305.05065 [cs.IR] https:\/\/arxiv.org\/abs\/2305.05065"},{"key":"e_1_3_2_1_30_1","volume-title":"Chi, and Xinyang Yi","author":"Singh Anima","year":"2024","unstructured":"Anima Singh, Trung Vu, Nikhil Mehta, Raghunandan Keshavan, Maheswaran Sathiamoorthy, Yilin Zheng, Lichan Hong, Lukasz Heldt, LiWei, Devansh Tandon, Ed H. Chi, and Xinyang Yi. 2024. Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations. arXiv:2306.08121 [cs.IR] https: \/\/arxiv.org\/abs\/2306.08121"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_32_1","volume-title":"Tuan Tran, Christophe Ropers, Eduardo S\u00e1nchez, Robin San Roman, Alexandre Mourachko, Safiyyah Saleem, and Holger Schwenk.","author":"LCM","year":"2024","unstructured":"LCM team, Lo\u00efc Barrault, Paul-Ambroise Duquenne, Maha Elbayad, Artyom Kozhevnikov, Belen Alastruey, Pierre Andrews, Mariano Coria, Guillaume Couairon, Marta R. Costa-juss\u00e0, David Dale, Hady Elsahar, Kevin Heffernan, Jo\u00e3o Maria Janeiro, Tuan Tran, Christophe Ropers, Eduardo S\u00e1nchez, Robin San Roman, Alexandre Mourachko, Safiyyah Saleem, and Holger Schwenk. 2024. Large Concept Models: Language Modeling in a Sentence Representation Space. arXiv:2412.08821 [cs.CL] https:\/\/arxiv.org\/abs\/2412.08821"},{"key":"e_1_3_2_1_33_1","volume-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction. Advances in neural information processing systems 37","author":"Tian Keyu","year":"2024","unstructured":"Keyu Tian, Yi Jiang, Zehuan Yuan, Bingyue Peng, and Liwei Wang. 2024. Visual autoregressive modeling: Scalable image generation via next-scale prediction. Advances in neural information processing systems 37 (2024), 84839-84865."},{"key":"e_1_3_2_1_34_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_35_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","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. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570372"},{"key":"e_1_3_2_1_37_1","first-page":"1785","volume-title":"Proceedings of the web conference","author":"Shivanna Rakesh","year":"2021","unstructured":"RuoxiWang, 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 Proceedings of the web conference 2021. 1785-1797."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599918"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481952"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3282907"},{"key":"e_1_3_2_1_41_1","unstructured":"Jiaqi Zhai Lucy Liao Xing Liu YuemingWang Rui Li Xuan Cao Leon Gao Zhaojie Gong Fangda Gu Michael He Yinghai Lu and Yu Shi. 2024. Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations. arXiv:2402.17152 [cs.LG] https:\/\/arxiv.org\/abs\/2402.17152"},{"key":"e_1_3_2_1_42_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. 2024. Wukong: Towards a scaling law for large-scale recommendation. arXiv preprint arXiv:2403.02545 (2024)."},{"key":"e_1_3_2_1_43_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_44_1","volume-title":"Breaking the curse of quality saturation with user-centric ranking. arXiv preprint arXiv:2305.15333","author":"Zhao Zhuokai","year":"2023","unstructured":"Zhuokai Zhao, Yang Yang, Wenyu Wang, Chihuang Liu, Yu Shi, Wenjie Hu, Haotian Zhang, and Shuang Yang. 2023. Breaking the curse of quality saturation with user-centric ranking. arXiv preprint arXiv:2305.15333 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Carolina Zheng Minhui Huang Dmitrii Pedchenko Kaushik Rangadurai Siyu Wang Gaby Nahum Jie Lei Yang Yang Tao Liu Zutian Luo XiaohanWei Dinesh Ramasamy Jiyan Yang Yiping Han Lin Yang Hangjun Xu Rong Jin and Shuang Yang. 2025. Enhancing Embedding Representation Stability in Recommendation Systems with Semantic ID. arXiv:2504.02137","DOI":"10.1145\/3705328.3748123"},{"key":"e_1_3_2_1_46_1","unstructured":"Guorui Zhou Jiaxin Deng Jinghao Zhang Kuo Cai Lejian Ren Qiang Luo Qianqian Wang Qigen Hu Rui Huang Shiyao Wang Weifeng Ding Wuchao Li Xinchen Luo Xingmei Wang Zexuan Cheng Zixing Zhang Bin Zhang Boxuan Wang Chaoyi Ma Chengru Song ChenhuiWang DiWang Dongxue Meng Fan Yang Fangyu Zhang Feng Jiang Fuxing Zhang Gang Wang Guowang Zhang Han Li Hengrui Hu Hezheng Lin Hongtao Cheng Hongyang Cao Huanjie Wang Jiaming Huang Jiapeng Chen Jiaqiang Liu Jinghui Jia Kun Gai Lantao Hu Liang Zeng Liao Yu QiangWang Qidong Zhou ShengzheWang Shihui He Shuang Yang Shujie Yang Sui Huang Tao Wu Tiantian He Tingting Gao Wei Yuan Xiao Liang Xiaoxiao Xu Xugang Liu Yan Wang Yi Wang Yiwu Liu Yue Song Yufei Zhang Yunfan Wu Yunfeng Zhao and Zhanyu Liu. 2025. OneRec Technical Report. arXiv:2506.13695 [cs.IR] https:\/\/arxiv.org\/abs\/2506.13695"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411954"}],"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":"2026-08-07T01:23:38Z","timestamp":1786065818000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818505"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":48,"alternative-id":["10.1145\/3770855.3818505","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818505","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"}}]}}