{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:56Z","timestamp":1786120856944,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China (NSFC)\/Research Grants Council (RGC) of Hong Kong Joint Research Scheme","award":["N_HKBU214\/24"],"award-info":[{"award-number":["N_HKBU214\/24"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818070","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"6033-6043","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GLaVis: Generative Latent Visual Queries for Multimodal Conversational Recommender Systems with MLLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7291-6104","authenticated-orcid":false,"given":"Ting","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5842-838X","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1427-4139","authenticated-orcid":false,"given":"Yuhan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et al. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang et al. 2024. A Survey on Evaluation of Large Language Models. ACM transactions on intelligent systems and technology V15 3 (2024) 1-45.","DOI":"10.1145\/3641289"},{"key":"e_1_3_2_1_4_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_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331226"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613755"},{"key":"e_1_3_2_1_7_1","unstructured":"Luke Friedman Sameer Ahuja David Allen Zhenning Tan Hakim Sidahmed Changbo Long Jun Xie Gabriel Schubiner Ajay Patel Harsh Lara et al. 2023. Leveraging Large Language Models in Conversational Recommender Systems. arXiv preprint arXiv:2305.07961 (2023)."},{"key":"e_1_3_2_1_8_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_1_9_1","volume-title":"Nicholas Jing Yuan, and Enhong Chen","author":"He Weidong","year":"2024","unstructured":"Weidong He, Zhi Li, Hao Wang, Tong Xu, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, and Enhong Chen. 2024. Multimodal Dialogue Systems via Capturing Context-aware Dependencies and Ordinal Information of Semantic Elements. ACM Transactions on Intelligent Systems and Technology, V15, 3 (2024), 1-25."},{"key":"e_1_3_2_1_10_1","first-page":"2","volume-title":"Proceedings of The 10th International Conference on Learning Representations, V1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. Proceedings of The 10th International Conference on Learning Representations, V1, 2 (2022), 3."},{"key":"e_1_3_2_1_11_1","volume-title":"Pasquale Lops, Giovanni Semeraro, and Li Chen.","author":"Jameson Anthony","year":"2015","unstructured":"Anthony Jameson, Martijn C Willemsen, Alexander Felfernig, Marco De Gemmis, Pasquale Lops, Giovanni Semeraro, and Li Chen. 2015. Human Decision Making and Recommender Systems. In Recommender systems handbook. Springer, 611-648."},{"key":"e_1_3_2_1_12_1","volume-title":"V54, 5","author":"Jannach Dietmar","year":"2021","unstructured":"Dietmar Jannach, Ahtsham Manzoor, Wanling Cai, and Li Chen. 2021. A survey on conversational recommender systems. ACM Computing Surveys (CSUR), V54, 5 (2021), 1-36."},{"key":"e_1_3_2_1_13_1","volume-title":"V20, 4","author":"J\u00e4rvelin Kalervo","year":"2002","unstructured":"Kalervo J\u00e4rvelin and Jaana Kek\u00e4l\u00e4inen. 2002. Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems (TOIS), V20, 4 (2002), 422-446."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736828"},{"key":"e_1_3_2_1_15_1","volume-title":"Vlm2vec: Training vision-language models for massive multimodal embedding tasks. arXiv preprint arXiv:2410.05160","author":"Jiang Ziyan","year":"2024","unstructured":"Ziyan Jiang, Rui Meng, Xinyi Yang, Semih Yavuz, Yingbo Zhou, and Wenhu Chen. 2024. Vlm2vec: Training vision-language models for massive multimodal embedding tasks. arXiv preprint arXiv:2410.05160 (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0939"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619119"},{"key":"e_1_3_2_1_18_1","volume-title":"A conversation is worth a thousand recommendations: A survey of holistic conversational recommender systems. arXiv preprint arXiv:2309.07682","author":"Li Chuang","year":"2023","unstructured":"Chuang Li, Hengchang Hu, Yan Zhang, Min-Yen Kan, and Haizhou Li. 2023a. A conversation is worth a thousand recommendations: A survey of holistic conversational recommender systems. arXiv preprint arXiv:2309.07682 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023b. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In Proceedings of the 40th International Conference on Machine Learning (Honolulu, Hawaii, USA) (ICML'23). JMLR.org, Article 814, 13 pages."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462970"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240605"},{"key":"e_1_3_2_1_22_1","volume-title":"MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs. arXiv preprint arXiv:2411.02571","author":"Lin Sheng-Chieh","year":"2024","unstructured":"Sheng-Chieh Lin, Chankyu Lee, Mohammad Shoeybi, Jimmy Lin, Bryan Catanzaro, and Wei Ping. 2024. MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs. arXiv preprint arXiv:2411.02571 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3108724"},{"key":"e_1_3_2_1_25_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_26_1","unstructured":"Kaicheng Pang Xingxing Zou and Waikeung Wong. 2025. FashionM3: Multimodal Multitask and Multiround Fashion Assistant based on Unified Vision-Language Model. arXiv:2504.17826 [cs.CV] https:\/\/arxiv.org\/abs\/2504.17826"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of The 38th 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 Proceedings of The 38th International Conference on Machine Learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv:1908.10084 [cs.CL] https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11331"},{"key":"e_1_3_2_1_31_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_1_32_1","unstructured":"Aaditya Singh Adam Fry Adam Perelman Adam Tart Adi Ganesh Ahmed El-Kishky Aidan McLaughlin Aiden Low AJ Ostrow Akhila Ananthram et al. 2025. OpenAI GPT-5 System Card. arXiv preprint arXiv:2601.03267 (2025)."},{"key":"e_1_3_2_1_33_1","volume-title":"Gemini: A Family of Highly Capable Multimodal Models. arXiv preprint arXiv:2312.11805","author":"Team Gemini","year":"2023","unstructured":"Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, et al., 2023. Gemini: A Family of Highly Capable Multimodal Models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_34_1","unstructured":"Qwen Team. 2025. Qwen3 Technical Report. arXiv:2505.09388 [cs.CL] https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_2_1_35_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et al. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 31th Annual Conference on Neural Information Processing Systems, V30","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. Proceedings of the 31th Annual Conference on Neural Information Processing Systems, V30 (2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.58"},{"key":"e_1_3_2_1_38_1","volume-title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers. In European Conference on Computer Vision. Springer, 387-404","author":"Wei Cong","year":"2024","unstructured":"Cong Wei, Yang Chen, Haonan Chen, Hexiang Hu, Ge Zhang, Jie Fu, Alan Ritter, and Wenhu Chen. 2024. UniIR: Training and Benchmarking Universal Multimodal Information Retrievers. In European Conference on Computer Vision. Springer, 387-404."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602070"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the 41th International Conference on Machine Learning.","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2024. NExT-GPT: Any-to-Any Multimodal LLM. In Proceedings of the 41th International Conference on Machine Learning."},{"key":"e_1_3_2_1_41_1","volume-title":"Weihao Wang, Kevin Qinghong Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, and Mike Zheng Shou.","author":"Xie Jinheng","year":"2024","unstructured":"Jinheng Xie, Weijia Mao, Zechen Bai, David Junhao Zhang, Weihao Wang, Kevin Qinghong Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, and Mike Zheng Shou. 2024. Show-o: One Single Transformer to Unify Multimodal Understanding and Generation. arXiv preprint arXiv:2408.12528 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688146"},{"key":"e_1_3_2_1_43_1","volume-title":"MM-LLMs: Recent Advances in MultiModal Large Language Models. arXiv preprint arXiv:2401.13601","author":"Zhang Duzhen","year":"2024","unstructured":"Duzhen Zhang, Yahan Yu, Jiahua Dong, Chenxing Li, Dan Su, Chenhui Chu, and Dong Yu. 2024. MM-LLMs: Recent Advances in MultiModal Large Language Models. arXiv preprint arXiv:2401.13601 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. arXiv:2205.01068 [cs.CL] https:\/\/arxiv.org\/abs\/2205.01068"},{"key":"e_1_3_2_1_45_1","unstructured":"Yuze Zhao Jintao Huang Jinghan Hu Xingjun Wang Yunlin Mao Daoze Zhang Zeyinzi Jiang Zhikai Wu Baole Ai Ang Wang Wenmeng Zhou and Yingda Chen. 2024. SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning. arXiv:2408.05517 [cs.CL] https:\/\/arxiv.org\/abs\/2408.05517"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:20:10Z","timestamp":1786065610000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":45,"alternative-id":["10.1145\/3770855.3818070","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818070","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}