{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T05:06:59Z","timestamp":1783141619491,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,22]]},"DOI":"10.1145\/3696410.3714764","type":"proceedings-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T22:47:11Z","timestamp":1745362031000},"page":"275-292","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["When Large Vision Language Models Meet Multimodal Sequential Recommendation: An Empirical Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6763-5236","authenticated-orcid":false,"given":"Peilin","family":"Zhou","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5323-2209","authenticated-orcid":false,"given":"Chao","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0301-1866","authenticated-orcid":false,"given":"Jing","family":"Ren","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6089-1657","authenticated-orcid":false,"given":"Xinfeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5169-3180","authenticated-orcid":false,"given":"Yueqi","family":"Xie","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8946-4228","authenticated-orcid":false,"given":"Meng","family":"Cao","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2113-5902","authenticated-orcid":false,"given":"Zhongtao","family":"Rao","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0587-9571","authenticated-orcid":false,"given":"You-Liang","family":"Huang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"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\/0009-0008-5513-8396","authenticated-orcid":false,"given":"Junling","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-6617","authenticated-orcid":false,"given":"Jae Boum","family":"Kim","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, 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\/0000-0001-7045-6503","authenticated-orcid":false,"given":"Raymond Chi-Wing","family":"Wong","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4478-9720","authenticated-orcid":false,"given":"Sunghun","family":"Kim","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Anthropic. 2024. The Claude 3 Model Family: Opus Sonnet Haiku. https:\/\/www-cdn.anthropic.com\/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627\/Model_Card_Claude_3.pdf"},{"key":"e_1_3_2_1_2_1","volume-title":"Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering10030380"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614978"},{"key":"e_1_3_2_1_5_1","volume-title":"Xing","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03--30-vicuna\/"},{"key":"e_1_3_2_1_6_1","volume-title":"Sampling techniques","author":"Cochran William G","year":"1977","unstructured":"William G Cochran. 1977. Sampling techniques. John Wiley& Sons (1977)."},{"key":"e_1_3_2_1_7_1","volume-title":"MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation","author":"Cui Qiang","year":"2020","unstructured":"Qiang Cui, Shu Wu, Qiang Liu, Wen Zhong, and Liang Wang. 2020. MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation. IEEE Transactions on Knowledge and Data Engineering (2020), 317--331."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3610646"},{"key":"e_1_3_2_1_9_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arxiv","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. arxiv: 1810.04805 [cs.CL]"},{"key":"e_1_3_2_1_10_1","volume-title":"Vito Walter Anelli, Fedelucio Narducci, Tommaso Di Noia, and Eugenio Di Sciascio.","author":"Palma Dario Di","year":"2023","unstructured":"Dario Di Palma, Giovanni Maria Biancofiore, Vito Walter Anelli, Fedelucio Narducci, Tommaso Di Noia, and Eugenio Di Sciascio. 2023. Evaluating chatgpt as a recommender system: A rigorous approach. arXiv preprint arXiv:2309.03613 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657725"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635805"},{"key":"e_1_3_2_1_13_1","volume-title":"Chat-rec: Towards interactive and explainable llms-augmented recommender system. arXiv preprint arXiv:2303.14524","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Tao Sheng, Youlin Xiang, Yun Xiong, Haofen Wang, and Jiawei Zhang. 2023. Chat-rec: Towards interactive and explainable llms-augmented recommender system. arXiv preprint arXiv:2303.14524 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458723"},{"key":"e_1_3_2_1_15_1","volume-title":"Vip5: Towards multimodal foundation models for recommendation. arXiv preprint arXiv:2305.14302","author":"Geng Shijie","year":"2023","unstructured":"Shijie Geng, Juntao Tan, Shuchang Liu, Zuohui Fu, and Yongfeng Zhang. 2023. Vip5: Towards multimodal foundation models for recommendation. arXiv preprint arXiv:2305.14302 (2023)."},{"key":"e_1_3_2_1_16_1","unstructured":"Team GLM Aohan Zeng Bin Xu Bowen Wang Chenhui Zhang Da Yin Diego Rojas Guanyu Feng Hanlin Zhao Hanyu Lai et al. 2024. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools. arXiv preprint arXiv:2406.12793 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614775"},{"key":"e_1_3_2_1_18_1","unstructured":"Glenn D Israel. 1992. Sampling the evidence of extension program impact. Citeseer."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_20_1","volume-title":"Determining sample size for research activities. Educational and psychological measurement","author":"Krejcie Robert V","year":"1970","unstructured":"Robert V Krejcie and Daryle W Morgan. 1970. Determining sample size for research activities. Educational and psychological measurement, Vol. 30, 3 (1970), 607--610."},{"key":"e_1_3_2_1_21_1","volume-title":"Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond. arXiv preprint arXiv:2402.10805","author":"Li Yongqi","year":"2024","unstructured":"Yongqi Li, Wenjie Wang, Leigang Qu, Liqiang Nie, Wenjie Li, and Tat-Seng Chua. 2024. Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond. arXiv preprint arXiv:2402.10805 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583378"},{"key":"e_1_3_2_1_23_1","volume-title":"Llara: Large language-recommendation assistant. Preprint","author":"Liao Jiayi","year":"2024","unstructured":"Jiayi Liao, Sihang Li, Zhengyi Yang, Jiancan Wu, Yancheng Yuan, Xiang Wang, and Xiangnan He. 2024. Llara: Large language-recommendation assistant. Preprint (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Lin Weizhe","year":"2024","unstructured":"Weizhe Lin, Jinghong Chen, Jingbiao Mei, Alexandru Coca, and Bill Byrne. 2024. Fine-grained late-interaction multi-modal retrieval for retrieval augmented visual question answering. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_25_1","unstructured":"Junling Liu Chao Liu Peilin Zhou Renjie Lv Kang Zhou and Yan Zhang. 2023b. Is ChatGPT a Good Recommender? A Preliminary Study. arxiv: 2304.10149 [cs.IR]"},{"key":"e_1_3_2_1_26_1","volume-title":"Yu","author":"Liu Junling","year":"2023","unstructured":"Junling Liu, Chao Liu, Peilin Zhou, Qichen Ye, Dading Chong, Kang Zhou, Yueqi Xie, Yuwei Cao, Shoujin Wang, Chenyu You, and Philip S. Yu. 2023c. LLMRec: Benchmarking Large Language Models on Recommendation Task. arxiv: 2308.12241 [cs.IR]"},{"key":"e_1_3_2_1_27_1","volume-title":"2023 d. Qilin-med-vl: Towards chinese large vision-language model for general healthcare. arXiv preprint arXiv:2310.17956","author":"Liu Junling","year":"2023","unstructured":"Junling Liu, Ziming Wang, Qichen Ye, Dading Chong, Peilin Zhou, and Yining Hua. 2023 d. Qilin-med-vl: Towards chinese large vision-language model for general healthcare. arXiv preprint arXiv:2310.17956 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Multimodal recommender systems: A survey. arXiv preprint arXiv:2302.03883","author":"Liu Qidong","year":"2023","unstructured":"Qidong Liu, Jiaxi Hu, Yutian Xiao, Jingtong Gao, and Xiangyu Zhao. 2023a. Multimodal recommender systems: A survey. arXiv preprint arXiv:2302.03883 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models. arXiv preprint arXiv:2402.08670","author":"Liu Yuqing","year":"2024","unstructured":"Yuqing Liu, Yu Wang, Lichao Sun, and Philip S Yu. 2024a. Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models. arXiv preprint arXiv:2402.08670 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Yu","author":"Liu Yuqing","year":"2024","unstructured":"Yuqing Liu, Yu Wang, Lichao Sun, and Philip S. Yu. 2024b. Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models. arxiv: 2402.08670 [cs.AI]"},{"key":"e_1_3_2_1_31_1","volume-title":"Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation. arXiv preprint arXiv:2401.13870","author":"Luo Sichun","year":"2024","unstructured":"Sichun Luo, Yuxuan Yao, Bowei He, Yinya Huang, Aojun Zhou, Xinyi Zhang, Yuanzhang Xiao, Mingjie Zhan, and Linqi Song. 2024. Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation. arXiv preprint arXiv:2401.13870 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755nolinkurl10.1145"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557101"},{"key":"e_1_3_2_1_36_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_37_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_38_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Wenhai","year":"2024","unstructured":"Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, et al. 2024. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_39_1","unstructured":"Tianxin Wei Bowen Jin Ruirui Li Hansi Zeng Zhengyang Wang Jianhui Sun Qingyu Yin Hanqing Lu Suhang Wang Jingrui He et al. 2024. Towards unified multi-modal personalization: Large vision-language models for generative recommendation and beyond. arXiv preprint arXiv:2403.10667 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the 27th ACM International Conference on Multimedia.","author":"Wei Yinwei","year":"2020","unstructured":"Yinwei Wei, Xiang Wang, Liqiang Nie, Xiangnan He, and Tat-Seng Chua. 2020. MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video. In Proceedings of the 27th ACM International Conference on Multimedia."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531963"},{"key":"e_1_3_2_1_42_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yang Xu","year":"2024","unstructured":"Xu Yang, Yongliang Wu, Mingzhuo Yang, Haokun Chen, and Xin Geng. 2024. Exploring diverse in-context configurations for image captioning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation. arXiv preprint arXiv:2408.09698","author":"Ye Yuyang","year":"2024","unstructured":"Yuyang Ye, Zhi Zheng, Yishan Shen, Tianshu Wang, Hengruo Zhang, Peijun Zhu, Runlong Yu, Kai Zhang, and Hui Xiong. 2024. Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation. arXiv preprint arXiv:2408.09698 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Large multi-modal encoders for recommendation. arXiv preprint arXiv:2310.20343","author":"Yi Zixuan","year":"2023","unstructured":"Zixuan Yi, Zijun Long, Iadh Ounis, Craig Macdonald, and Richard Mccreadie. 2023. Large multi-modal encoders for recommendation. arXiv preprint arXiv:2310.20343 (2023)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591932"},{"key":"e_1_3_2_1_46_1","volume-title":"Dong Wang, and Even Oldridge.","author":"Yue Zhenrui","year":"2023","unstructured":"Zhenrui Yue, Sara Rabhi, Gabriel de Souza Pereira Moreira, Dong Wang, and Even Oldridge. 2023. LlamaRec: Two-stage recommendation using large language models for ranking. arXiv preprint arXiv:2311.02089 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Exploring recommendation capabilities of gpt-4v (ision): A preliminary case study. arXiv preprint arXiv:2311.04199","author":"Zhou Peilin","year":"2023","unstructured":"Peilin Zhou, Meng Cao, You-Liang Huang, Qichen Ye, Peiyan Zhang, Junling Liu, Yueqi Xie, Yining Hua, and Jaeboum Kim. 2023a. Exploring recommendation capabilities of gpt-4v (ision): A preliminary case study. arXiv preprint arXiv:2311.04199 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645661"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611943"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714764","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714764","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:41Z","timestamp":1750295921000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714764"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":49,"alternative-id":["10.1145\/3696410.3714764","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714764","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}