{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:06:50Z","timestamp":1775840810094,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","funder":[{"name":"National Science Foundation of China","award":["U22B2059, 62276083"],"award-info":[{"award-number":["U22B2059, 62276083"]}]},{"name":"Key Research and Development Program of Heilongjiang Province","award":["2024ZX01A05"],"award-info":[{"award-number":["2024ZX01A05"]}]},{"name":"5G Application Innovation Joint Research Institute","award":["A003"],"award-info":[{"award-number":["A003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792790","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"7999-8007","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond the Flat Sequence: Hierarchical and Preference-Aware Generative Recommendations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3226-619X","authenticated-orcid":false,"given":"Zerui","family":"Chen","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4978-8041","authenticated-orcid":false,"given":"Heng","family":"Chang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3155-7832","authenticated-orcid":false,"given":"Tianying","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1276-0202","authenticated-orcid":false,"given":"Chuantian","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4222-8439","authenticated-orcid":false,"given":"Yi","family":"Cao","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8123-9889","authenticated-orcid":false,"given":"Jiandong","family":"Ding","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7915-1001","authenticated-orcid":false,"given":"Ming","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2543-5604","authenticated-orcid":false,"given":"Bing","family":"Qin","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"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","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3465055"},{"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":"Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509","author":"Child Rewon","year":"2019","unstructured":"Rewon Child, Scott Gray, Alec Radford, and Ilya Sutskever. 2019. Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)."},{"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":"Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691","author":"Dao Tri","year":"2023","unstructured":"Tri Dao. 2023. Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in neural information processing systems","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in neural information processing systems, Vol. 35 (2022), 16344-16359."},{"key":"e_1_3_2_1_10_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_1_12_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_13_1","volume-title":"MTGR: Industrial-Scale Generative Recommendation Framework in Meituan. arXiv preprint arXiv:2505.18654","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., 2025. MTGR: Industrial-Scale Generative Recommendation Framework in Meituan. arXiv preprint arXiv:2505.18654 (2025)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271761"},{"key":"e_1_3_2_1_15_1","volume-title":"Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939","author":"Hidasi Bal\u00e1zs","year":"2015","unstructured":"Bal\u00e1zs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939 (2015)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357814"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00619"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330984"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_1_22_1","volume-title":"Large language models: A survey. arXiv preprint arXiv:2402.06196","author":"Minaee Shervin","year":"2024","unstructured":"Shervin Minaee, Tomas Mikolov, Narjes Nikzad, Meysam Chenaghlu, Richard Socher, Xavier Amatriain, and Jianfeng Gao. 2024. Large language models: A survey. arXiv preprint arXiv:2402.06196 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16557"},{"key":"e_1_3_2_1_24_1","first-page":"68658","article-title":"Flashattention-3: Fast and accurate attention with asynchrony and low-precision","volume":"37","author":"Shah Jay","year":"2024","unstructured":"Jay Shah, Ganesh Bikshandi, Ying Zhang, Vijay Thakkar, Pradeep Ramani, and Tri Dao. 2024. Flashattention-3: Fast and accurate attention with asynchrony and low-precision. Advances in Neural Information Processing Systems, Vol. 37 (2024), 68658-68685.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_1_27_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_28_1","volume-title":"Attention is all you need. 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, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450078"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3440207"},{"key":"e_1_3_2_1_31_1","volume-title":"Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768","author":"Wang Sinong","year":"2020","unstructured":"Sinong Wang, Belinda Z Li, Madian Khabsa, Han Fang, and Hao Ma. 2020. Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01291-2"},{"key":"e_1_3_2_1_33_1","volume-title":"Item Cluster-aware Prompt Learning for Session-based Recommendation. arXiv preprint arXiv:2410.04756","author":"Yang Wooseong","year":"2024","unstructured":"Wooseong Yang, Chen Wang, Zihe Song, Weizhi Zhang, and Philip S Yu. 2024. Item Cluster-aware Prompt Learning for Session-based Recommendation. arXiv preprint arXiv:2410.04756 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"Knowledge transfer via pre-training for recommendation: A review and prospect. Frontiers in big Data","author":"Zeng Zheni","year":"2021","unstructured":"Zheni Zeng, Chaojun Xiao, Yuan Yao, Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin, and Maosong Sun. 2021. Knowledge transfer via pre-training for recommendation: A review and prospect. Frontiers in big Data, Vol. 4 (2021), 602071."},{"key":"e_1_3_2_1_35_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_36_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_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3285029"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219823"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411954"},{"key":"e_1_3_2_1_40_1","volume-title":"A survey on efficient training of transformers. arXiv preprint arXiv:2302.01107","author":"Zhuang Bohan","year":"2023","unstructured":"Bohan Zhuang, Jing Liu, Zizheng Pan, Haoyu He, Yuetian Weng, and Chunhua Shen. 2023. A survey on efficient training of transformers. arXiv preprint arXiv:2302.01107 (2023)."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:18:37Z","timestamp":1775837917000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792790"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":40,"alternative-id":["10.1145\/3774904.3792790","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792790","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}