{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:05:34Z","timestamp":1784138734123,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":16,"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":"Guangdong provincial project","award":["2023CX10X008"],"award-info":[{"award-number":["2023CX10X008"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809977","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"4074-4079","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Structural and Disentangled Adaptation of Large Vision Language Models for Multimodal Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2113-5902","authenticated-orcid":false,"given":"Zhongtao","family":"Rao","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6763-5236","authenticated-orcid":false,"given":"Peilin","family":"Zhou","sequence":"additional","affiliation":[{"name":"New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3495-522X","authenticated-orcid":false,"given":"Dading","family":"Chong","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1331-2827","authenticated-orcid":false,"given":"Zhiwei","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1133-9379","authenticated-orcid":false,"given":"Shoujin","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2832-0295","authenticated-orcid":false,"given":"Nan","family":"Tang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"arXiv preprint arXiv:2502.13923","author":"Bai Shuai","year":"2025","unstructured":"Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, Jiabo Ye, Xi Zhang, Tianbao Xie, Zesen Cheng, Hang Zhang, Zhibo Yang, Haiyang Xu, and Junyang Lin. 2025. Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_1_3_1","volume-title":"Lora: Low-rank adaptation of large language models. ICLR, V1, 2","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, V1, 2 (2022), 3."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_5_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. 2024. Multimodal recommender systems: A survey. Comput. Surveys, V57, 2 (2024), 1-17.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Qidong Liu Xian Wu Wanyu Wang Yejing Wang Yuanshao Zhu Xiangyu Zhao Feng Tian and Yefeng Zheng. 2025. LLMEmb: large language model can be a good embedding generator for sequential recommendation. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence (AAAI'25\/IAAI'25\/EAAI'25). AAAI Press Article 1354 9 pages. doi:10.1609\/aaai.v39i11.33327","DOI":"10.1609\/aaai.v39i11.33327"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_1_8_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_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187556"},{"key":"e_1_3_2_1_11_1","article-title":"A survey on multimodal large language models","volume":"11","author":"Yin Shukang","year":"2024","unstructured":"Shukang Yin, Chaoyou Fu, Sirui Zhao, Ke Li, Xing Sun, Tong Xu, and Enhong Chen. 2024. A survey on multimodal large language models. National Science Review, V11, 12 (2024).","journal-title":"National Science Review"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613915"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608786"},{"key":"e_1_3_2_1_14_1","volume-title":"When Large Vision Language Models Meet Multimodal Sequential Recommendation: An Empirical Study. In THE WEB CONFERENCE","author":"Zhou Peilin","year":"2025","unstructured":"Peilin Zhou, Chao Liu, Jing Ren, Xinfeng Zhou, Yueqi XIE, Meng Cao, Zhongtao Rao, You-Liang Huang, Dading Chong, Junling Liu, et al., 2025. When Large Vision Language Models Meet Multimodal Sequential Recommendation: An Empirical Study. In THE WEB CONFERENCE 2025."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614785"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611380.3628561"}],"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":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:17:46Z","timestamp":1784135866000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809977"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":16,"alternative-id":["10.1145\/3805712.3809977","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809977","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"}}]}}