{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:33:12Z","timestamp":1783737192440,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62222209"],"award-info":[{"award-number":["No.62222209"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Beijing National Research Center For Information Science And Technology","doi-asserted-by":"publisher","award":["No.BNR2023TD03006"],"award-info":[{"award-number":["No.BNR2023TD03006"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733273","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:04Z","timestamp":1750876264000},"page":"1507-1516","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Aligning Large Multimodal Model with Sequential Recommendation via Content-Behavior Guidance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4389-2980","authenticated-orcid":false,"given":"Zihao","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0351-2939","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4978-8041","authenticated-orcid":false,"given":"Heng","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0943-2286","authenticated-orcid":false,"given":"Hong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4057-5138","authenticated-orcid":false,"given":"Lifeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716--23736."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608857"},{"key":"e_1_3_2_1_3_1","volume-title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. arXiv preprint arXiv:2312.14238","author":"Chen Zhe","year":"2023","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, and Jifeng Dai. 2023. InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. arXiv preprint arXiv:2312.14238 (2023)."},{"key":"e_1_3_2_1_4_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_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_6_1","volume-title":"Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046","author":"Fan Wenqi","year":"2023","unstructured":"Wenqi Fan, Zihuai Zhao, Jiatong Li, Yunqing Liu, Xiaowei Mei, Yiqi Wang, Jiliang Tang, and Qing Li. 2023. Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482242"},{"key":"e_1_3_2_1_8_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_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33274"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.644"},{"key":"e_1_3_2_1_12_1","volume-title":"2nd International Conference on Learning Representations, ICLR","author":"Goodfellow Ian J.","year":"2014","unstructured":"Ian J. Goodfellow, Mehdi Mirza, Xia Da, Aaron C. Courville, and Yoshua Bengio. 2014. An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks. In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14--16, 2014, Conference Track Proceedings."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"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","unstructured":"Wenyi Hong Weihan Wang Qingsong Lv Jiazheng Xu Wenmeng Yu Junhui Ji Yan Wang Zihan Wang Yuxiao Dong Ming Ding and Jie Tang. 2023. CogAgent: A Visual Language Model for GUI Agents. arxiv: 2312.08914 [cs.CV]"},{"key":"e_1_3_2_1_17_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624918.3625339"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635850"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403226"},{"key":"e_1_3_2_1_23_1","volume-title":"Multimodal foundation models: From specialists to general-purpose assistants. arXiv preprint arXiv:2309.10020","author":"Li Chunyuan","year":"2023","unstructured":"Chunyuan Li, Zhe Gan, Zhengyuan Yang, Jianwei Yang, Linjie Li, Lijuan Wang, and Jianfeng Gao. 2023b. Multimodal foundation models: From specialists to general-purpose assistants. arXiv preprint arXiv:2309.10020 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3050571"},{"key":"e_1_3_2_1_25_1","volume-title":"E4SRec: An elegant effective efficient extensible solution of large language models for sequential recommendation. arXiv preprint arXiv:2312.02443","author":"Li Xinhang","year":"2023","unstructured":"Xinhang Li, Chong Chen, Xiangyu Zhao, Yong Zhang, and Chunxiao Xing. 2023a. E4SRec: An elegant effective efficient extensible solution of large language models for sequential recommendation. arXiv preprint arXiv:2312.02443 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning. arXiv preprint arXiv:2303.15647","author":"Lialin Vladislav","year":"2023","unstructured":"Vladislav Lialin, Vijeta Deshpande, and Anna Rumshisky. 2023. Scaling down to scale up: A guide to parameter-efficient fine-tuning. arXiv preprint arXiv:2303.15647 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"LLaRA: Aligning large language models with sequential recommenders. arXiv preprint arXiv:2312.02445","author":"Liao Jiayi","year":"2023","unstructured":"Jiayi Liao, Sihang Li, Zhengyi Yang, Jiancan Wu, Yancheng Yuan, Xiang Wang, and Xiangnan He. 2023. LLaRA: Aligning large language models with sequential recommenders. arXiv preprint arXiv:2312.02445 (2023)."},{"key":"e_1_3_2_1_28_1","unstructured":"Jianghao Lin Xinyi Dai Yunjia Xi Weiwen Liu Bo Chen Xiangyang Li Chenxu Zhu Huifeng Guo Yong Yu Ruiming Tang et al. 2023. How can recommender systems benefit from large language models: A survey. arXiv preprint arXiv:2306.05817 (2023)."},{"key":"e_1_3_2_1_29_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li and Yong Jae Lee. 2023a. Improved Baselines with Visual Instruction Tuning."},{"key":"e_1_3_2_1_30_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024a. LLaVA-NeXT: Improved reasoning OCR and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01--30-llava-next\/"},{"key":"e_1_3_2_1_31_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024b. Visual instruction tuning. In Advances in Neural Information Processing Systems, Vol. 36. Curran Associates, Inc., 34892--34916."},{"key":"e_1_3_2_1_32_1","volume-title":"GPT understands, too. AI Open","author":"Liu Xiao","year":"2023","unstructured":"Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2023b. GPT understands, too. AI Open (2023)."},{"key":"e_1_3_2_1_33_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. 2024c. Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models. arXiv preprint arXiv:2402.08670 (2024)."},{"key":"e_1_3_2_1_34_1","unstructured":"Chaochao Lu Chen Qian Guodong Zheng Hongxing Fan Hongzhi Gao Jie Zhang Jing Shao Jingyi Deng Jinlan Fu Kexin Huang et al. 2024. From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability Trustworthiness and Causality through Four Modalities. arXiv preprint arXiv:2401.15071 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Llm-rec: Personalized recommendation via prompting large language models. arXiv preprint arXiv:2307.15780","author":"Lyu Hanjia","year":"2023","unstructured":"Hanjia Lyu, Song Jiang, Hanqing Zeng, Yinglong Xia, and Jiebo Luo. 2023. Llm-rec: Personalized recommendation via prompting large language models. arXiv preprint arXiv:2307.15780 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403091"},{"key":"e_1_3_2_1_37_1","volume-title":"A content-driven micro-video recommendation dataset at scale. arXiv preprint arXiv:2309.15379","author":"Ni Yongxin","year":"2023","unstructured":"Yongxin Ni, Yu Cheng, Xiangyan Liu, Junchen Fu, Youhua Li, Xiangnan He, Yongfeng Zhang, and Fajie Yuan. 2023. A content-driven micro-video recommendation dataset at scale. arXiv preprint arXiv:2309.15379 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688123"},{"key":"e_1_3_2_1_39_1","volume-title":"ControlRec: Bridging the semantic gap between language model and personalized recommendation. arXiv preprint arXiv:2311.16441","author":"Qiu Junyan","year":"2023","unstructured":"Junyan Qiu, Haitao Wang, Zhaolin Hong, Yiping Yang, Qiang Liu, and Xingxing Wang. 2023. ControlRec: Bridging the semantic gap between language model and personalized recommendation. arXiv preprint arXiv:2311.16441 (2023)."},{"key":"e_1_3_2_1_40_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_41_1","volume-title":"Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. 452--461","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. 452--461."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159656"},{"key":"e_1_3_2_1_45_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_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767694"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3675164"},{"key":"e_1_3_2_1_48_1","volume-title":"International Conference on Machine Learning. PMLR, 36174--36192","author":"Wang Xin","year":"2023","unstructured":"Xin Wang, Zirui Pan, Yuwei Zhou, Hong Chen, Chendi Ge, and Wenwu Zhu. 2023. Curriculum co-disentangled representation learning across multiple environments for social recommendation. In International Conference on Machine Learning. PMLR, 36174--36192."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635853"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612709"},{"key":"e_1_3_2_1_51_1","volume-title":"Large language model can interpret latent space of sequential recommender. arXiv preprint arXiv:2310.20487","author":"Yang Zhengyi","year":"2023","unstructured":"Zhengyi Yang, Jiancan Wu, Yanchen Luo, Jizhi Zhang, Yancheng Yuan, An Zhang, Xiang Wang, and Xiangnan He. 2023. Large language model can interpret latent space of sequential recommender. arXiv preprint arXiv:2310.20487 (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33426"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290975"},{"key":"e_1_3_2_1_54_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_55_1","volume-title":"NoteLLM-2: Multimodal Large Representation Models for Recommendation. arXiv preprint arXiv:2405.16789","author":"Zhang Chao","year":"2024","unstructured":"Chao Zhang, Haoxin Zhang, Shiwei Wu, Di Wu, Tong Xu, Yan Gao, Yao Hu, and Enhong Chen. 2024b. NoteLLM-2: Multimodal Large Representation Models for Recommendation. arXiv preprint arXiv:2405.16789 (2024)."},{"key":"e_1_3_2_1_56_1","volume-title":"Leyu Lin, and Ji-Rong Wen.","author":"Zhang Junjie","year":"2023","unstructured":"Junjie Zhang, Ruobing Xie, Yupeng Hou, Wayne Xin Zhao, Leyu Lin, and Ji-Rong Wen. 2023. Recommendation as instruction following: A large language model empowered recommendation approach. arXiv preprint arXiv:2305.07001 (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3701988","article-title":"Disentangled Dynamic Graph Attention Network for Out-of-Distribution Sequential Recommendation","volume":"43","author":"Zhang Zeyang","year":"2024","unstructured":"Zeyang Zhang, Xin Wang, Haibo Chen, Haoyang Li, and Wenwu Zhu. 2024a. Disentangled Dynamic Graph Attention Network for Out-of-Distribution Sequential Recommendation. ACM Transactions on Information Systems, Vol. 43, 1 (2024), 1--42.","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411954"},{"key":"e_1_3_2_1_59_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=1tZbq88f27","author":"Zhu Deyao","year":"2024","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2024. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=1tZbq88f27"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733273","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:07:05Z","timestamp":1755749225000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733273"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":59,"alternative-id":["10.1145\/3731715.3733273","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733273","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}