{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:10:22Z","timestamp":1765339822975,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2422610, U23A20386, 62276045, 62293542, 6244101029"],"award-info":[{"award-number":["2422610, U23A20386, 62276045, 62293542, 6244101029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Liao Ning Province Science and Technology Plan","award":["023JH26, 10200016"],"award-info":[{"award-number":["023JH26, 10200016"]}]},{"name":"Dalian City Science and Technology Innovation Fund","award":["023JJ11CG001"],"award-info":[{"award-number":["023JJ11CG001"]}]},{"name":"Ningbo Science and Technology Innovation Project","award":["2024Z294"],"award-info":[{"award-number":["2024Z294"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755289","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"9996-10005","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GLDesigner: Leveraging Multi-Modal LLMs as Designer for Enhanced Aesthetic Text Glyph Layouts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9314-4242","authenticated-orcid":false,"given":"Junwen","family":"He","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1911-2526","authenticated-orcid":false,"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2538-8358","authenticated-orcid":false,"given":"Lijun","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6473-5784","authenticated-orcid":false,"given":"Chenyang","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1886-3325","authenticated-orcid":false,"given":"Hanyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0053-7892","authenticated-orcid":false,"given":"Jin-Peng","family":"Lan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6628-6924","authenticated-orcid":false,"given":"Jun-Yan","family":"He","sequence":"additional","affiliation":[{"name":"Alibaba Group, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9427-8251","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"Kingdee Group, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3257-2746","authenticated-orcid":false,"given":"Yifeng","family":"Geng","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Anthropic. 2024. Introducing the next generation of Claude. https:\/\/www. anthropic.com\/news\/claude-3-family."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01343"},{"key":"e_1_3_2_1_3_1","volume-title":"Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, ShijieWang, Sinan Tan, PengWang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548332"},{"key":"e_1_3_2_1_5_1","volume-title":"Textdiffuser-2: Unleashing the power of language models for text rendering. arXiv preprint arXiv:2311.16465","author":"Chen Jingye","year":"2023","unstructured":"Jingye Chen, Yupan Huang, Tengchao Lv, Lei Cui, Qifeng Chen, and Furu Wei. 2023. Textdiffuser-2: Unleashing the power of language models for text rendering. arXiv preprint arXiv:2311.16465 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Textdiffuser: Diffusion models as text painters. Advances in Neural Information Processing Systems 36","author":"Chen Jingye","year":"2024","unstructured":"Jingye Chen, Yupan Huang, Tengchao Lv, Lei Cui, Qifeng Chen, and Furu Wei. 2024. Textdiffuser: Diffusion models as text painters. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. arXiv preprint arXiv:2312.14238","author":"Chen Zhe","year":"2023","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, and Jifeng Dai. 2023. InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. arXiv preprint arXiv:2312.14238 (2023)."},{"key":"e_1_3_2_1_8_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Xin Eric Wang, and William Yang Wang","author":"Feng Weixi","year":"2024","unstructured":"Weixi Feng, Wanrong Zhu, Tsu-jui Fu, Varun Jampani, Arjun Akula, Xuehai He, Sugato Basu, Xin Eric Wang, and William Yang Wang. 2024. Layoutgpt: Compositional visual planning and generation with large language models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems 27","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 27 (2014)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00104"},{"key":"e_1_3_2_1_12_1","unstructured":"Jun-Yan He Zhi-Qi Cheng Chenyang Li Jingdong Sun Wangmeng Xiang Xianhui Lin Xiaoyang Kang Zengke Jin Yusen Hu Bin Luo et al. 2023. Wordart designer: User-driven artistic typography synthesis using large language models. arXiv preprint arXiv:2310.18332 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00583"},{"key":"e_1_3_2_1_15_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_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00193"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00980"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01765"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00999"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475497"},{"key":"e_1_3_2_1_22_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_29"},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR","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. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_25_1","volume-title":"Layoutgan: Generating graphic layouts with wireframe discriminators. arXiv preprint arXiv:1901.06767","author":"Li Jianan","year":"2019","unstructured":"Jianan Li, Jimei Yang, Aaron Hertzmann, Jianming Zhang, and Tingfa Xu. 2019. Layoutgan: Generating graphic layouts with wireframe discriminators. arXiv preprint arXiv:1901.06767 (2019)."},{"key":"e_1_3_2_1_26_1","volume-title":"Analogical reasoning on chinese morphological and semantic relations. arXiv preprint arXiv:1805.06504","author":"Li Shen","year":"2018","unstructured":"Shen Li, Zhe Zhao, Renfen Hu,Wensi Li, Tao Liu, and Xiaoyong Du. 2018. Analogical reasoning on chinese morphological and semantic relations. arXiv preprint arXiv:1805.06504 (2018)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02159"},{"key":"e_1_3_2_1_28_1","volume-title":"LayoutPrompter: Awaken the Design Ability of Large Language Models. In Thirty-seventh Conference on Neural Information Processing Systems.","author":"Lin Jiawei","year":"2023","unstructured":"Jiawei Lin, Jiaqi Guo, Shizhao Sun, Zijiang James Yang, Jian-Guang Lou, and Dongmei Zhang. 2023. LayoutPrompter: Awaken the Design Ability of Large Language Models. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_29_1","unstructured":"Haotian Liu Chunyuan Li QingyangWu and Yong Jae Lee. 2023. Visual Instruction Tuning. In NeurIPS."},{"key":"e_1_3_2_1_30_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov I","year":"2017","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01480"},{"key":"e_1_3_2_1_32_1","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"e_1_3_2_1_33_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_34_1","volume-title":"Improved techniques for training gans. Advances in neural information processing systems 29","author":"Salimans Tim","year":"2016","unstructured":"Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved techniques for training gans. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. PMLR, 2256-2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. PMLR, 2256-2265."},{"key":"e_1_3_2_1_36_1","volume-title":"Layoutnuwa: Revealing the hidden layout expertise of large language models. arXiv preprint arXiv:2309.09506","author":"Tang Zecheng","year":"2023","unstructured":"Zecheng Tang, Chenfei Wu, Juntao Li, and Nan Duan. 2023. Layoutnuwa: Revealing the hidden layout expertise of large language models. arXiv preprint arXiv:2309.09506 (2023)."},{"key":"e_1_3_2_1_37_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_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00247"},{"key":"e_1_3_2_1_39_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_40_1","volume-title":"See Kiong Ng, and Jiashi Feng","author":"Xu Lin","year":"2024","unstructured":"Lin Xu, Yilin Zhao, Daquan Zhou, Zhijie Lin, See Kiong Ng, and Jiashi Feng. 2024. Pllava: Parameter-free llava extension from images to videos for video dense captioning. arXiv preprint arXiv:2404.16994 (2024)."},{"key":"e_1_3_2_1_41_1","unstructured":"Tao Yang Yingmin Luo Zhongang Qi Yang Wu Ying Shan and Chang Wen Chen. 2024. PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM. arXiv:2406.02884 [cs.CV] https:\/\/arxiv.org\/abs\/2406.02884"},{"key":"e_1_3_2_1_42_1","volume-title":"DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models. arXiv preprint arXiv:2405.20985","author":"Yao Linli","year":"2024","unstructured":"Linli Yao, Lei Li, Shuhuai Ren, LeanWang, Yuanxin Liu, Xu Sun, and Lu Hou. 2024. DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models. arXiv preprint arXiv:2405.20985 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Caiming Xiong, and Ran Xu.","author":"Yu Ning","year":"2022","unstructured":"Ning Yu, Chia-Chih Chen, Zeyuan Chen, Rui Meng, GangWu, Paul Josel, Juan Carlos Niebles, Caiming Xiong, and Ran Xu. 2022. LayoutDETR: detection transformer is a good multimodal layout designer. arXiv preprint arXiv:2212.09877 (2022)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00664"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_46_1","volume-title":"Composition-aware graphic layout GAN for visual-textual presentation designs. arXiv preprint arXiv:2205.00303","author":"Zhou Min","year":"2022","unstructured":"Min Zhou, Chenchen Xu, Ye Ma, Tiezheng Ge, Yuning Jiang, and Weiwei Xu. 2022. Composition-aware graphic layout GAN for visual-textual presentation designs. arXiv preprint arXiv:2205.00303 (2022)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:08:14Z","timestamp":1765339694000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755289"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":46,"alternative-id":["10.1145\/3746027.3755289","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755289","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}