{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:05:50Z","timestamp":1784138750918,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NSF","award":["IIS~2504090"],"award-info":[{"award-number":["IIS~2504090"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809844","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"4414-4418","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Unimodal Perspectives: Generative Retrieval with Multimodal Semantics"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5364-151X","authenticated-orcid":false,"given":"Jing","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, Ann Arbor, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9054-3856","authenticated-orcid":false,"given":"Mingxuan","family":"Ju","sequence":"additional","affiliation":[{"name":"Snap Inc., Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2107-504X","authenticated-orcid":false,"given":"Yozen","family":"Liu","sequence":"additional","affiliation":[{"name":"Snap Inc., Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5524-4232","authenticated-orcid":false,"given":"Shubham","family":"Vij","sequence":"additional","affiliation":[{"name":"Snap Inc., Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3206-8179","authenticated-orcid":false,"given":"Danai","family":"Koutra","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, Ann Arbor, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3261-8430","authenticated-orcid":false,"given":"Neil","family":"Shah","sequence":"additional","affiliation":[{"name":"Snap Inc., Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7660-1732","authenticated-orcid":false,"given":"Tong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Snap Inc., Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671474"},{"key":"e_1_3_2_1_3_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_4_1","first-page":"54","article-title":"A survey of sequential pattern mining","volume":"1","author":"Fournier-Viger Philippe","year":"2017","unstructured":"Philippe Fournier-Viger, Jerry Chun-Wei Lin, Rage Uday Kiran, Yun Sing Koh, and Rincy Thomas. 2017. A survey of sequential pattern mining. Data Science and Pattern Recognition, Vol. 1, 1 (2017), 54-77.","journal-title":"Data Science and Pattern Recognition"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_1_6_1","volume-title":"International conference on machine learning. PMLR, 4651-4664","author":"Jaegle Andrew","year":"2021","unstructured":"Andrew Jaegle, Felix Gimeno, Andy Brock, Oriol Vinyals, Andrew Zisserman, and Joao Carreira. 2021. Perceiver: General perception with iterative attention. In International conference on machine learning. PMLR, 4651-4664."},{"key":"e_1_3_2_1_7_1","unstructured":"Bowen Jin Hansi Zeng Guoyin Wang Xiusi Chen Tianxin Wei Ruirui Li Zhengyang Wang Zheng Li Yang Li Hanqing Lu et al. 2024. Language models as semantic indexers. ICML (2024)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671884"},{"key":"e_1_3_2_1_10_1","volume-title":"Mmgrec: Multimodal generative recommendation with transformer model. arXiv preprint arXiv:2404.16555","author":"Liu Han","year":"2024","unstructured":"Han Liu, Yinwei Wei, Xuemeng Song, Weili Guan, Yuan-Fang Li, and Liqiang Nie. 2024b. Mmgrec: Multimodal generative recommendation with transformer model. arXiv preprint arXiv:2404.16555 (2024)."},{"key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Multimodal recommender systems: A survey","volume":"57","author":"Liu Qidong","year":"2024","unstructured":"Qidong Liu, Jiaxi Hu, Yutian Xiao, Xiangyu Zhao, Jingtong Gao, Wanyu Wang, Qing Li, and Jiliang Tang. 2024a. Multimodal recommender systems: A survey. Comput. Surveys, Vol. 57, 2 (2024), 1-17.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","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, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_14_1","volume-title":"Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Tran, Jonah Samost, et al.","author":"Rajput Shashank","year":"2023","unstructured":"Shashank Rajput, Nikhil Mehta, Anima Singh, Raghunandan Hulikal Keshavan, Trung Vu, Lukasz Heldt, Lichan Hong, Yi Tay, Vinh Tran, Jonah Samost, et al., 2023. Recommender systems with generative retrieval. Advances in Neural Information Processing Systems, Vol. Recommender Systems with Generative Retrieval (2023), 10299-10315."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_3_2_1_16_1","volume-title":"E-commerce recommendation applications. Data mining and knowledge discovery","author":"Schafer J Ben","year":"2001","unstructured":"J Ben Schafer, Joseph A Konstan, and John Riedl. 2001. E-commerce recommendation applications. Data mining and knowledge discovery, Vol. 5 (2001), 115-153."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_19_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Sun Weiwei","year":"2024","unstructured":"Weiwei Sun, Lingyong Yan, Zheng Chen, Shuaiqiang Wang, Haichao Zhu, Pengjie Ren, Zhumin Chen, Dawei Yin, Maarten Rijke, and Zhaochun Ren. 2024. Learning to tokenize for generative retrieval. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, et al.","author":"Tschannen Michael","year":"2025","unstructured":"Michael Tschannen, Alexey Gritsenko, Xiao Wang, Muhammad Ferjad Naeem, Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, et al., 2025. Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679569"},{"key":"e_1_3_2_1_22_1","volume-title":"Multimodal learning with transformers: A survey","author":"Xu Peng","year":"2023","unstructured":"Peng Xu, Xiatian Zhu, and David A Clifton. 2023. Multimodal learning with transformers: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29035-0_4"},{"key":"e_1_3_2_1_24_1","volume-title":"Multimodal Quantitative Language for Generative Recommendation. The Thirteenth International Conference on Learning Representations","author":"Zhai Jianyang","year":"2025","unstructured":"Jianyang Zhai, Zi-Feng Mai, Chang-Dong Wang, Feidiao Yang, Xiawu Zheng, Hui Li, and Yonghong Tian. 2025. Multimodal Quantitative Language for Generative Recommendation. The Thirteenth International Conference on Learning Representations (2025)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00118"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645347"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3805712.3809844","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:23:42Z","timestamp":1784136222000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809844"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":26,"alternative-id":["10.1145\/3805712.3809844","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809844","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}