{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T18:03:33Z","timestamp":1779991413423,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3774905.3795725","type":"proceedings-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:14:56Z","timestamp":1779988496000},"page":"753-764","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Triple Modality Fusion: Aligning Visual, Textual, and Graph Data for LLM-based Multi-Behavior Recommender Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7454-3959","authenticated-orcid":false,"given":"Luyi","family":"Ma","sequence":"first","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3156-1989","authenticated-orcid":false,"given":"Xiaohan","family":"Li","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9594-1021","authenticated-orcid":false,"given":"Zezhong","family":"Fan","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1040-0211","authenticated-orcid":false,"given":"Kai","family":"Zhao","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3702-528X","authenticated-orcid":false,"given":"Jianpeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8106-2961","authenticated-orcid":false,"given":"Jason","family":"Cho","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1606-8409","authenticated-orcid":false,"given":"Praveen","family":"Kanumala","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4859-2937","authenticated-orcid":false,"given":"Kaushiki","family":"Nag","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7754-3652","authenticated-orcid":false,"given":"Evren","family":"Korpeoglu","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5643-5263","authenticated-orcid":false,"given":"Sushant","family":"Kumar","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9186-3175","authenticated-orcid":false,"given":"Kannan","family":"Achan","sequence":"additional","affiliation":[{"name":"Walmart Global Tech, Sunnyvale, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608857"},{"key":"e_1_3_2_1_2_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_3_1","volume-title":"M6-rec: Generative pretrained language models are open-ended recommender systems. arXiv preprint arXiv:2205.08084","author":"Cui Zeyu","year":"2022","unstructured":"Zeyu Cui, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. M6-rec: Generative pretrained language models are open-ended recommender systems. arXiv preprint arXiv:2205.08084 (2022)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3610646"},{"key":"e_1_3_2_1_5_1","volume-title":"9th International Conference on Learning Representations, ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations, ICLR 2021."},{"key":"e_1_3_2_1_6_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_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_1_8_1","first-page":"9606","article-title":"VIP5","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. In Findings of EMNLP. 9606-9620.","journal-title":"Towards Multimodal Foundation Models for Recommendation. In Findings of EMNLP."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"e_1_3_2_1_10_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_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539381"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_24"},{"key":"e_1_3_2_1_13_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR.","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 The Tenth International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401072"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599519"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00041"},{"key":"e_1_3_2_1_18_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_19_1","volume-title":"Is chatgpt a good recommender? a preliminary study. arXiv preprint arXiv:2304.10149","author":"Liu Junling","year":"2023","unstructured":"Junling Liu, Chao Liu, Peilin Zhou, Renjie Lv, Kang Zhou, and Yan Zhang. 2023. Is chatgpt a good recommender? a preliminary study. arXiv preprint arXiv:2304.10149 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16557"},{"key":"e_1_3_2_1_21_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_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657821"},{"key":"e_1_3_2_1_25_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_26_1","unstructured":"Hugo Touvron Louis Martin Kevin R. Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Daniel M. Bikel Lukas Blecher Cristian Cant\u00f3n Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony S. Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel M. Kloumann A. V. Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith R. Subramanian Xia Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zhengxu Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. ArXiv abs\/2307.09288 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259950998"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671636"},{"key":"e_1_3_2_1_28_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"key":"e_1_3_2_1_30_1","first-page":"6099","article-title":"Multi-behavior sequential recommendation with temporal graph transformer","volume":"35","author":"Xia Lianghao","year":"2022","unstructured":"Lianghao Xia, Chao Huang, Yong Xu, and Jian Pei. 2022. Multi-behavior sequential recommendation with temporal graph transformer. IEEE Transactions on Knowledge and Data Engineering 35, 6 (2022), 6099-6112.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462972"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570386"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539342"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539090"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186146"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532023"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557330"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018665"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774905.3795725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:17:31Z","timestamp":1779988651000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774905.3795725"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":38,"alternative-id":["10.1145\/3774905.3795725","10.1145\/3774905"],"URL":"https:\/\/doi.org\/10.1145\/3774905.3795725","relation":{},"subject":[],"published":{"date-parts":[[2026,5,28]]},"assertion":[{"value":"2026-05-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}