{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:04:50Z","timestamp":1784138690303,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":38,"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":"University Grants Committee","award":["17209822"],"award-info":[{"award-number":["17209822"]}]},{"name":"Innovation and Technology Commission","award":["ITS\/383\/23FP"],"award-info":[{"award-number":["ITS\/383\/23FP"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809623","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"2096-2106","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Well Begun is Half Done: Training-Free and Model-Agnostic Semantically Guaranteed User Representation Initialization for Multimodal Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7876-3740","authenticated-orcid":false,"given":"Jinfeng","family":"Xu","sequence":"first","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5779-3523","authenticated-orcid":false,"given":"Zheyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1638-9623","authenticated-orcid":false,"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6749-5442","authenticated-orcid":false,"given":"Jinze","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6952-0886","authenticated-orcid":false,"given":"Hewei","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4762-5943","authenticated-orcid":false,"given":"Jianheng","family":"Tang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1717-5785","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Macao Polytechnic University, Macao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4952-699X","authenticated-orcid":false,"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3454-8731","authenticated-orcid":false,"given":"Edith C. H.","family":"Ngai","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331254"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730251"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28688"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_2_2_6_1","volume-title":"Large Language Model Interaction Simulator for Cold-Start Item Recommendation. arXiv preprint arXiv:2402.09176","author":"Huang Feiran","year":"2024","unstructured":"Feiran Huang, Zhenghang Yang, Junyi Jiang, Yuanchen Bei, Yijie Zhang, and Hao Chen. 2024. Large Language Model Interaction Simulator for Cold-Start Item Recommendation. arXiv preprint arXiv:2402.09176 (2024)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Yangqin Jiang Lianghao Xia Wei Wei Da Luo Kangyi Lin and Chao Huang. 2024. DiffMM: Multi-Modal Diffusion Model for Recommendation. (2024).","DOI":"10.1145\/3664647.3681498"},{"key":"e_1_3_2_2_8_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371841"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Shang Liu Zhenzhong Chen Hongyi Liu and Xinghai Hu. 2019. User-video co-attention network for personalized micro-video recommendation. In The world wide web conference. 3020-3026.","DOI":"10.1145\/3308558.3313513"},{"key":"e_1_3_2_2_11_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_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_2_13_1","unstructured":"Leheng Sheng An Zhang Yi Zhang Yuxin Chen Xiang Wang and Tat-Seng Chua. 2025. Language Representations Can be What Recommenders Need: Findings and Potentials. In ICLR."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2893638"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187556"},{"key":"e_1_3_2_2_16_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_2_17_1","volume-title":"Dualgnn: Dual graph neural network for multimedia recommendation","author":"Wang Qifan","year":"2021","unstructured":"Qifan Wang, Yinwei Wei, Jianhua Yin, Jianlong Wu, Xuemeng Song, and Liqiang Nie. 2021. Dualgnn: Dual graph neural network for multimedia recommendation. IEEE Transactions on Multimedia (2021)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583206"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635853"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737042"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679697"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3760909"},{"key":"e_1_3_2_2_25_1","volume-title":"Raymond Chi-Wing Wong, and Edith CH Ngai","author":"Xu Jinfeng","year":"2025","unstructured":"Jinfeng Xu, Zheyu Chen, Jinze Li, Shuo Yang, Wei Wang, Xiping Hu, Raymond Chi-Wing Wong, and Edith CH Ngai. 2025b. Enhancing Robustness and Generalization Capability for Multimodal Recommender Systems via Sharpness-Aware Minimization. IEEE Transactions on Knowledge and Data Engineering (2025)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729927"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755781"},{"key":"e_1_3_2_2_28_1","volume-title":"2025 f. VI-MMRec: Similarity-Aware Training Cost-free Virtual User-Item Interactions for Multimodal Recommendation. arXiv preprint arXiv:2512.08702","author":"Xu Jinfeng","year":"2025","unstructured":"Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li, Zitong Wan, Hewei Wang, Weijie Liu, Yijie Li, and Edith CH Ngai. 2025 f. VI-MMRec: Similarity-Aware Training Cost-free Virtual User-Item Interactions for Multimodal Recommendation. arXiv preprint arXiv:2512.08702 (2025)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33408"},{"key":"e_1_3_2_2_30_1","volume-title":"A survey on multimodal recommender systems: Recent advances and future directions","author":"Xu Jinfeng","year":"2026","unstructured":"Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li, Wei Wang, Xiping Hu, Steven Hoi, and Edith Ngai. 2026. A survey on multimodal recommender systems: Recent advances and future directions. IEEE Transactions on Multimedia (2026)."},{"key":"e_1_3_2_2_31_1","volume-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421","author":"Yang Zhengyuan","year":"2023","unstructured":"Zhengyuan Yang, Linjie Li, Kevin Lin, Jianfeng Wang, Chung-Ching Lin, Zicheng Liu, and Lijuan Wang. 2023. The dawn of lmms: Preliminary explorations with gpt-4v (ision). arXiv preprint arXiv:2309.17421, Vol. 9, 1 (2023), 1."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613915"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475259"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3221949"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230631"},{"key":"e_1_3_2_2_36_1","volume-title":"MMRec: Simplifying Multimodal Recommendation. arXiv preprint arXiv:2302.03497","author":"Zhou Xin","year":"2023","unstructured":"Xin Zhou. 2023. MMRec: Simplifying Multimodal Recommendation. arXiv preprint arXiv:2302.03497 (2023)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611943"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"}],"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":"2026-07-15T17:15:12Z","timestamp":1784135712000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809623"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":38,"alternative-id":["10.1145\/3805712.3809623","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809623","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"}}]}}