{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:40:08Z","timestamp":1783737608888,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":34,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Quan Cheng Laboratory","award":["Grant No. QCLZD202301"],"award-info":[{"award-number":["Grant No. QCLZD202301"]}]},{"name":"Natural Science Foundation of China","award":["Grant No. U21B2026, 62372260"],"award-info":[{"award-number":["Grant No. U21B2026, 62372260"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,22]]},"DOI":"10.1145\/3696410.3714733","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T16:42:02Z","timestamp":1746463322000},"page":"2076-2084","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Explainable Multi-Modality Alignment for Transferable Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6896-4268","authenticated-orcid":false,"given":"Shenghao","family":"Yang","sequence":"first","affiliation":[{"name":"DCST, Tsinghua University, Quan Cheng Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5604-7527","authenticated-orcid":false,"given":"Weizhi","family":"Ma","sequence":"additional","affiliation":[{"name":"AIR, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9393-4854","authenticated-orcid":false,"given":"Zhiqiang","family":"Guo","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3158-1920","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Quan Cheng Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7314-7618","authenticated-orcid":false,"given":"Haiyang","family":"Wu","sequence":"additional","affiliation":[{"name":"Machine learning platform department, Tencent TEG, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6504-0312","authenticated-orcid":false,"given":"Junjie","family":"Zhai","sequence":"additional","affiliation":[{"name":"Machine learning platform department, Tencent TEG, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2850-9048","authenticated-orcid":false,"given":"Chunhui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8709-3128","authenticated-orcid":false,"given":"Yuekui","family":"Yang","sequence":"additional","affiliation":[{"name":"DCST, Tsinghua University, Beijing, China and Machine learning platform department, Tencent TEG, Beijing, 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":"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 35 (2022) 23716--23736."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_3_1","volume-title":"Zeroshot recommender systems. arXiv preprint arXiv:2105.08318","author":"Ding Hao","year":"2021","unstructured":"Hao Ding, Yifei Ma, Anoop Deoras, Yuyang Wang, and Hao Wang. 2021. Zeroshot recommender systems. arXiv preprint arXiv:2105.08318 (2021)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28688"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_1_8_1","volume-title":"Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders. arXiv preprint arXiv:2210.12316","author":"Hou Yupeng","year":"2022","unstructured":"Yupeng Hou, Zhankui He, Julian McAuley, and Wayne Xin Zhao. 2022. Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders. arXiv preprint arXiv:2210.12316 (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539381"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271684"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00380"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657701"},{"key":"e_1_3_2_1_14_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems 36","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems 36 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251108"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Julian McAuley Christopher Targett Qinfeng Shi and Anton van den Hengel. 2015. Image-based Recommendations on Styles and Substitutes. arXiv:1506.04757 [cs.CV]","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_2_1_17_1","volume-title":"X-instructblip: A framework for aligning x-modal instruction-aware representations to llms and emergent cross-modal reasoning. arXiv preprint arXiv:2311.18799","author":"Panagopoulou Artemis","year":"2023","unstructured":"Artemis Panagopoulou, Le Xue, Ning Yu, Junnan Li, Dongxu Li, Shafiq Joty, Ran Xu, Silvio Savarese, Caiming Xiong, and Juan Carlos Niebles. 2023. X-instructblip: A framework for aligning x-modal instruction-aware representations to llms and emergent cross-modal reasoning. arXiv preprint arXiv:2311.18799 (2023)."},{"key":"e_1_3_2_1_18_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_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645458"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401969"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3187556"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611967"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 27th ACM international conference on multimedia. 1437--1445","author":"Nie Liqiang","year":"2019","unstructured":"YinweiWei, XiangWang, Liqiang Nie, Xiangnan He, Richang Hong, and Tat-Seng Chua. 2019. MMGCN: Multi-modal graph convolution network for personalized recommendation of micro-video. In Proceedings of the 27th ACM international conference on multimedia. 1437--1445."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations. 38--45","author":"Debut Lysandre","year":"2020","unstructured":"ThomasWolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, et al. 2020. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations. 38--45."},{"key":"e_1_3_2_1_25_1","volume-title":"Ptum: Pre-training user model from unlabeled user behaviors via self-supervision. arXiv preprint arXiv:2010.01494","author":"Wu Chuhan","year":"2020","unstructured":"Chuhan Wu, Fangzhao Wu, Tao Qi, Jianxun Lian, Yongfeng Huang, and Xing Xie. 2020. Ptum: Pre-training user model from unlabeled user behaviors via self-supervision. arXiv preprint arXiv:2010.01494 (2020)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00082"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613915"},{"key":"e_1_3_2_1_28_1","volume-title":"Where to Go Next for Recommender Systems? ID-vs. Modality-based recommender models revisited. arXiv preprint arXiv:2303.13835","author":"Yuan Zheng","year":"2023","unstructured":"Zheng Yuan, Fajie Yuan, Yu Song, Youhua Li, Junchen Fu, Fei Yang, Yunzhu Pan, and Yongxin Ni. 2023. Where to Go Next for Recommender Systems? ID-vs. Modality-based recommender models revisited. arXiv preprint arXiv:2303.13835 (2023)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482016"},{"key":"e_1_3_2_1_30_1","volume-title":"Chatbridge: Bridging modalities with large language model as a language catalyst. arXiv preprint arXiv:2305.16103","author":"Zhao Zijia","year":"2023","unstructured":"Zijia Zhao, Longteng Guo, Tongtian Yue, Sihan Chen, Shuai Shao, Xinxin Zhu, Zehuan Yuan, and Jing Liu. 2023. Chatbridge: Bridging modalities with large language model as a language catalyst. arXiv preprint arXiv:2305.16103 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230631"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611943"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357992"}],"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\/3696410.3714733","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714733","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\/3696410.3714733"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":34,"alternative-id":["10.1145\/3696410.3714733","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714733","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"}}]}}