{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:00:25Z","timestamp":1765339225192,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","funder":[{"name":"National Science Foundation of China","award":["62072232"],"award-info":[{"award-number":["62072232"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754898","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"5970-5978","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Harnessing Multimodal Large Language Models for Personalized Product Search with Query-aware Refinement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4931-9867","authenticated-orcid":false,"given":"Beibei","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0467-4650","authenticated-orcid":false,"given":"Yanan","family":"Lu","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-5647","authenticated-orcid":false,"given":"Ruobing","family":"Xie","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4459-4977","authenticated-orcid":false,"given":"Zongyi","family":"Li","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7694-4879","authenticated-orcid":false,"given":"Siyuan","family":"Xing","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3092-424X","authenticated-orcid":false,"given":"Tongwei","family":"Ren","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8728-3475","authenticated-orcid":false,"given":"Fen","family":"Lin","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357980"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482276"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080813"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3361738"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401192"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462911"},{"key":"e_1_3_2_1_7_1","volume-title":"Reng Chiz Der, and Christian Bizer","author":"Brinkmann Alexander","year":"2023","unstructured":"Alexander Brinkmann, Roee Shraga, Reng Chiz Der, and Christian Bizer. 2023. Product Information Extraction using ChatGPT. In arXiv preprint arXiv:2306.14921."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3522672"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al., 2024. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511954"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599287"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511949"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615022"},{"key":"e_1_3_2_1_14_1","first-page":"1","volume-title":"ACM Transactions on Information Systems","volume":"37","author":"Guo Yangyang","unstructured":"Yangyang Guo, Zhiyong Cheng, Liqiang Nie, Yinglong Wang, Jun Ma, and Mohan Kankanhalli. [n.d.]. Attentive long short-term preference modeling for personalized product search. In ACM Transactions on Information Systems, Vol. 37. 1-27."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240541"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380051"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511964"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411936"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783381"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3473337"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645458"},{"key":"e_1_3_2_1_23_1","volume-title":"SEMINAR: Search Enhanced Multi-modal Interest Network and Approximate Retrieval for Lifelong Sequential Recommendation. In arXiv preprint arXiv:2407.10714.","author":"Shen Kaiming","year":"2024","unstructured":"Kaiming Shen, Xichen Ding, Zixiang Zheng, Yuqi Gong, Qianqian Li, Zhongyi Liu, and Guannan Zhang. 2024. SEMINAR: Search Enhanced Multi-modal Interest Network and Approximate Retrieval for Lifelong Sequential Recommendation. In arXiv preprint arXiv:2407.10714."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557351"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657811"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_27_1","first-page":"443","article-title":"Joint Personalized Search and Recommendation with Hypergraph Convolutional Networks","volume":"13185","author":"Thonet Thibaut","year":"2022","unstructured":"Thibaut Thonet, Jean-Michel Renders, Mario Choi, and Jinho Kim. 2022. Joint Personalized Search and Recommendation with Hypergraph Convolutional Networks. Advances in Information Retrieval, Vol. 13185, 443-456.","journal-title":"Advances in Information Retrieval"},{"key":"e_1_3_2_1_28_1","unstructured":"Ghazaleh Haratinezhad Torbati Anna Tigunova Andrew Yates and Gerhard Weikum. 2023. Recommendations by Concise User Profiles from Review Text. In arXiv preprint arXiv:2311.01314."},{"key":"e_1_3_2_1_29_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Yang Fan Kai Dang Mengfei Du Xuancheng Ren Rui Men Dayiheng Liu Chang Zhou Jingren Zhou and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. In arXiv preprint arXiv:2409.12191."},{"key":"e_1_3_2_1_30_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems, Vol. 35. 24824-24837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the International Conference on Learning Representations. 1-19","author":"Wei Tianxin","year":"2024","unstructured":"Tianxin Wei, Bowen Jin, Ruirui Li, Hansi Zeng, Zhengyang Wang, Jianhui Sun, Qingyu Yin, Hanqing Lu, Suhang Wang, Jingrui He, and Xianfeng Tang. 2024. Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond. In Proceedings of the International Conference on Learning Representations. 1-19."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3609225"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512036"},{"key":"e_1_3_2_1_34_1","unstructured":"Jiahao Wu Qijiong Liu Hengchang Hu Wenqi Fan Shengcai Liu Qing Li Xiao-Ming Wu and Ke Tang. 2025. TF-DCon: Leveraging Large Language Models (LLMs) to Empower Training-Free Dataset Condensation for Content-Based Recommendation. In arXiv preprint arXiv:2310.09874."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688104"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358057"},{"key":"e_1_3_2_1_37_1","unstructured":"An Yang Baosong Yang Beichen Zhang and et al. 2024. Qwen2.5 Technical Report. In arXiv preprint arXiv:2412.15115."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591932"},{"key":"e_1_3_2_1_39_1","volume-title":"Recommendation as instruction following: A large language model empowered recommendation approach. ACM Transactions on Information Systems","author":"Zhang Junjie","year":"2024","unstructured":"Junjie Zhang, Ruobing Xie, Yupeng Hou, Xin Zhao, Leyu Lin, and Ji-Rong Wen. 2024. Recommendation as instruction following: A large language model empowered recommendation approach. ACM Transactions on Information Systems (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:58:26Z","timestamp":1765339106000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754898"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":39,"alternative-id":["10.1145\/3746027.3754898","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754898","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}