{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T04:21:12Z","timestamp":1778559672522,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The Overseas Research Cooperation Fund of Tsinghua Shenzhen International Graduate School","award":["HW2021013"],"award-info":[{"award-number":["HW2021013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589334.3645633","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"3833-3843","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":26,"title":["PMG : Personalized Multimodal Generation with Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9559-3293","authenticated-orcid":false,"given":"Xiaoteng","family":"Shen","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8132-6250","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"www.ruizhang.info, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6001-1260","authenticated-orcid":false,"given":"Xiaoyan","family":"Zhao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5666-8320","authenticated-orcid":false,"given":"Jieming","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1521-9542","authenticated-orcid":false,"given":"Xi","family":"Xiao","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Tallrec: An effective and efficient tuning framework to align large language model with recommendation. arXiv preprint arXiv:2305.00447","author":"Bao Keqin","year":"2023","unstructured":"Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. 2023. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. arXiv preprint arXiv:2305.00447 (2023)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330652"},{"key":"e_1_3_2_2_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_2_4_1","volume-title":"Can: Creative adversarial networks, generating\" art\" by learning about styles and deviating from style norms. arXiv preprint arXiv:1706.07068","author":"Elgammal Ahmed","year":"2017","unstructured":"Ahmed Elgammal, Bingchen Liu, Mohamed Elhoseiny, and Marian Mazzone. 2017. Can: Creative adversarial networks, generating\" art\" by learning about styles and deviating from style norms. arXiv preprint arXiv:1706.07068 (2017)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"e_1_3_2_2_6_1","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618","author":"Gal Rinon","year":"2022","unstructured":"Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)."},{"key":"e_1_3_2_2_7_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_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546767"},{"key":"e_1_3_2_2_9_1","volume-title":"VIP5: Towards Multimodal Foundation Models for Recommendation. arXiv preprint arXiv:2305.14302","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. arXiv preprint arXiv:2305.14302 (2023)."},{"key":"e_1_3_2_2_10_1","volume-title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model. arXiv preprint arXiv:2304.13731","author":"Ghosal Deepanway","year":"2023","unstructured":"Deepanway Ghosal, Navonil Majumder, Ambuj Mehrish, and Soujanya Poria. 2023. Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model. arXiv preprint arXiv:2304.13731 (2023)."},{"key":"e_1_3_2_2_11_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems , Vol. 27 (2014)."},{"key":"e_1_3_2_2_12_1","volume-title":"A neural representation of sketch drawings. arXiv preprint arXiv:1704.03477","author":"Ha David","year":"2017","unstructured":"David Ha and Douglas Eck. 2017. A neural representation of sketch drawings. arXiv preprint arXiv:1704.03477 (2017)."},{"key":"e_1_3_2_2_13_1","volume-title":"The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis)","author":"Maxwell Harper F","year":"2015","unstructured":"F Maxwell Harper and Joseph A Konstan. 2015. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), Vol. 5, 4 (2015), 1--19."},{"key":"e_1_3_2_2_14_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems , Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_2_15_1","volume-title":"Large language models are zero-shot rankers for recommender systems. arXiv preprint arXiv:2305.08845","author":"Hou Yupeng","year":"2023","unstructured":"Yupeng Hou, Junjie Zhang, Zihan Lin, Hongyu Lu, Ruobing Xie, Julian McAuley, and Wayne Xin Zhao. 2023. Large language models are zero-shot rankers for recommender systems. arXiv preprint arXiv:2305.08845 (2023)."},{"key":"e_1_3_2_2_16_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_2_17_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_2_18_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Koh Jing Yu","year":"2024","unstructured":"Jing Yu Koh, Daniel Fried, and Russ R Salakhutdinov. 2024. Generating images with multimodal language models. Advances in Neural Information Processing Systems , Vol. 36 (2024)."},{"key":"e_1_3_2_2_19_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_2_20_1","volume-title":"Zhengxiao Du, Zhilin Yang, and Jie Tang.","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Lam Tam, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2021. P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602 (2021)."},{"key":"e_1_3_2_2_21_1","volume-title":"Audio, Video, and Text Integration. arXiv preprint arXiv:2306.09093","author":"Lyu Chenyang","year":"2023","unstructured":"Chenyang Lyu, Minghao Wu, Longyue Wang, Xinting Huang, Bingshuai Liu, Zefeng Du, Shuming Shi, and Zhaopeng Tu. 2023. Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration. arXiv preprint arXiv:2306.09093 (2023)."},{"key":"e_1_3_2_2_22_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_23_1","unstructured":"OpenAI. 2024. Video Generation Models as World Simulators. https:\/\/openai.com\/research\/video-generation-models-as-world-simulators."},{"key":"e_1_3_2_2_24_1","volume-title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation. arXiv preprint arXiv:2308.05095","author":"Qu Leigang","year":"2023","unstructured":"Leigang Qu, Shengqiong Wu, Hao Fei, Liqiang Nie, and Tat-Seng Chua. 2023. LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation. arXiv preprint arXiv:2308.05095 (2023)."},{"key":"e_1_3_2_2_25_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_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_27_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015: 18th International Conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015: 18th International Conference, Munich, Germany, October 5--9, 2015, Proceedings, Part III 18. Springer, 234--241."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_2_29_1","volume-title":"STEM: Unleashing the Power of Embeddings for Multi-task Recommendation. arXiv preprint arXiv:2308.13537","author":"Su Liangcai","year":"2023","unstructured":"Liangcai Su, Junwei Pan, Ximei Wang, Xi Xiao, Shijie Quan, Xihua Chen, and Jie Jiang. 2023. STEM: Unleashing the Power of Embeddings for Multi-task Recommendation. arXiv preprint arXiv:2308.13537 (2023)."},{"key":"e_1_3_2_2_30_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611967"},{"key":"e_1_3_2_2_32_1","volume-title":"Zero-Shot Next-Item Recommendation using Large Pretrained Language Models. arXiv preprint arXiv:2304.03153","author":"Wang Lei","year":"2023","unstructured":"Lei Wang and Ee-Peng Lim. 2023. Zero-Shot Next-Item Recommendation using Large Pretrained Language Models. arXiv preprint arXiv:2304.03153 (2023)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539382"},{"key":"e_1_3_2_2_34_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_2_37_1","volume-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671","author":"Wu Chenfei","year":"2023","unstructured":"Chenfei Wu, Shengming Yin, Weizhen Qi, Xiaodong Wang, Zecheng Tang, and Nan Duan. 2023. Visual chatgpt: Talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671 (2023)."},{"key":"e_1_3_2_2_38_1","volume-title":"Diffsound: Discrete diffusion model for text-to-sound generation","author":"Yang Dongchao","year":"2023","unstructured":"Dongchao Yang, Jianwei Yu, Helin Wang, Wen Wang, Chao Weng, Yuexian Zou, and Dong Yu. 2023. Diffsound: Discrete diffusion model for text-to-sound generation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2023)."},{"key":"e_1_3_2_2_39_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi Chaoya Jiang Chenliang Li Yuanhong Xu Hehong Chen Junfeng Tian Qian Qi Ji Zhang and Fei Huang. 2023. mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality. arxiv: 2304.14178 [cs.CL]"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_2_41_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023). io"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645633","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3645633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:20:56Z","timestamp":1755822056000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645633"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":41,"alternative-id":["10.1145\/3589334.3645633","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3645633","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}