{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:04:39Z","timestamp":1765343079501,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758269","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"13156-13163","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9426-9230","authenticated-orcid":false,"given":"Jinke","family":"Li","sequence":"first","affiliation":[{"name":"Zhejiang University, Haining, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6327-6811","authenticated-orcid":false,"given":"Jiarui","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4545-596X","authenticated-orcid":false,"given":"Chenxing","family":"Wei","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0074-2664","authenticated-orcid":false,"given":"Hande","family":"Dong","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2005-6170","authenticated-orcid":false,"given":"Qiang","family":"Lin","sequence":"additional","affiliation":[{"name":"Tencent, ShenZhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3294-0879","authenticated-orcid":false,"given":"Liangjing","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Haining, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6781-3442","authenticated-orcid":false,"given":"Zhicai","family":"Wang","sequence":"additional","affiliation":[{"name":"Independent Researcher, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0695-1566","authenticated-orcid":false,"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, Anhui, 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":"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 Vol. 35 (2022) 23716-23736."},{"key":"e_1_3_2_1_2_1","unstructured":"Anthropic. 2023. Claude 3.7 Sonnet System Card. Technical Report. Anthropic."},{"key":"e_1_3_2_1_3_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_4_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang Humen Zhong Yuanzhi Zhu Mingkun Yang Zhaohai Li Jianqiang Wan Pengfei Wang Wei Ding Zheren Fu Yiheng Xu Jiabo Ye Xi Zhang Tianbao Xie Zesen Cheng Hang Zhang Zhibo Yang Haiyang Xu and Junyang Lin. 2025. Qwen2.5-VL Technical Report. arXiv:2502.13923 [cs.CV] https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"e_1_3_2_1_5_1","volume-title":"Language models are few-shot learners. arXiv preprint arXiv:2005.14165","author":"Brown Tom B","year":"2020","unstructured":"Tom B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)."},{"key":"e_1_3_2_1_6_1","unstructured":"Alexandre Carlier Martin Danelljan Alexandre Alahi and Radu Timofte. 2020. DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation. arXiv:2007.11301 [cs.CV] https:\/\/arxiv.org\/abs\/2007.11301"},{"key":"e_1_3_2_1_7_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_8_1","unstructured":"Kevin Frans L. B. Soros and Olaf Witkowski. 2021. CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders. arXiv:2106.14843 [cs.CV] https:\/\/arxiv.org\/abs\/2106.14843"},{"key":"e_1_3_2_1_9_1","volume-title":"G-llava: Solving geometric problem with multi-modal large language model. arXiv preprint arXiv:2312.11370","author":"Gao Jiahui","year":"2023","unstructured":"Jiahui Gao, Renjie Pi, Jipeng Zhang, Jiacheng Ye, Wanjun Zhong, Yufei Wang, Lanqing Hong, Jianhua Han, Hang Xu, Zhenguo Li, et al., 2023. G-llava: Solving geometric problem with multi-modal large language model. arXiv preprint arXiv:2312.11370 (2023)."},{"key":"e_1_3_2_1_10_1","unstructured":"Ziyu Guo Renrui Zhang Xiangyang Zhu Yiwen Tang Xianzheng Ma Jiaming Han Kexin Chen Peng Gao Xianzhi Li Hongsheng Li et al. 2023. Point-bind & point-llm: Aligning point cloud with multi-modality for 3d understanding generation and instruction following. arXiv preprint arXiv:2309.00615 (2023)."},{"key":"e_1_3_2_1_11_1","unstructured":"David Ha and Douglas Eck. 2017. A Neural Representation of Sketch Drawings. arXiv:1704.03477 [cs.NE] https:\/\/arxiv.org\/abs\/1704.03477"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5772\/37435"},{"key":"e_1_3_2_1_13_1","first-page":"20482","article-title":"3d-llm: Injecting the 3d world into large language models","volume":"36","author":"Hong Yining","year":"2023","unstructured":"Yining Hong, Haoyu Zhen, Peihao Chen, Shuhong Zheng, Yilun Du, Zhenfang Chen, and Chuang Gan. 2023. 3d-llm: Injecting the 3d world into large language models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 20482-20494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681294"},{"key":"e_1_3_2_1_15_1","unstructured":"Ajay Jain Amber Xie and Pieter Abbeel. 2022. VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models. arXiv:2211.11319 [cs.CV] https:\/\/arxiv.org\/abs\/2211.11319"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00190"},{"key":"e_1_3_2_1_17_1","volume-title":"Socratic Chart: Cooperating Multiple Agents for Robust SVG Chart Understanding. arXiv:2504.09764 [cs.CV] https:\/\/arxiv.org\/abs\/2504.09764","author":"Ji Yuyang","year":"2025","unstructured":"Yuyang Ji and Haohan Wang. 2025. Socratic Chart: Cooperating Multiple Agents for Robust SVG Chart Understanding. arXiv:2504.09764 [cs.CV] https:\/\/arxiv.org\/abs\/2504.09764"},{"key":"e_1_3_2_1_18_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al., 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. Minneapolis, Minnesota, 2."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_21_1","volume-title":"Visual question answering instruction: Unlocking multimodal large language model to domain-specific visual multitasks. arXiv preprint arXiv:2402.08360","author":"Lee Jusung","year":"2024","unstructured":"Jusung Lee, Sungguk Cha, Younghyun Lee, and Cheoljong Yang. 2024. Visual question answering instruction: Unlocking multimodal large language model to domain-specific visual multitasks. arXiv preprint arXiv:2402.08360 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Mimic-it: Multi-modal in-context instruction tuning. arXiv preprint arXiv:2306.05425","author":"Li Bo","year":"2023","unstructured":"Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Fanyi Pu, Jingkang Yang, Chunyuan Li, and Ziwei Liu. 2023. Mimic-it: Multi-modal in-context instruction tuning. arXiv preprint arXiv:2306.05425 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895","author":"Li Feng","year":"2024","unstructured":"Feng Li, Renrui Zhang, Hao Zhang, Yuanhan Zhang, Bo Li, Wei Li, Zejun Ma, and Chunyuan Li. 2024. Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888-12900."},{"key":"e_1_3_2_1_25_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li and Yong Jae Lee. 2023. Improved Baselines with Visual Instruction Tuning."},{"key":"e_1_3_2_1_26_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024. LLaVA-NeXT: Improved reasoning OCR and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"e_1_3_2_1_27_1","unstructured":"Raphael Gontijo Lopes David Ha Douglas Eck and Jonathon Shlens. 2019. A Learned Representation for Scalable Vector Graphics. arXiv:1904.02632 [cs.CV] https:\/\/arxiv.org\/abs\/1904.02632"},{"key":"e_1_3_2_1_28_1","volume-title":"Macaw-llm: Multi-modal language modeling with image, 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_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01583"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34679"},{"key":"e_1_3_2_1_31_1","volume-title":"SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities. arXiv preprint arXiv:2404.13710","author":"Nishina Kunato","year":"2024","unstructured":"Kunato Nishina and Yusuke Matsui. 2024. SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities. arXiv preprint arXiv:2404.13710 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"https:\/\/openai.com\/index\/gpt-4v-system-card\/","author":"System Card AI.","year":"2023","unstructured":"OpenAI. 2023. GPT-4V(ision) System Card. (2023). https:\/\/openai.com\/index\/gpt-4v-system-card\/"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2003.1218261"},{"key":"e_1_3_2_1_34_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_35_1","unstructured":"Nikhila Ravi Valentin Gabeur Yuan-Ting Hu Ronghang Hu Chaitanya Ryali Tengyu Ma Haitham Khedr Roman R\u00e4dle Chloe Rolland Laura Gustafson et al. 2024. Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)."},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 7342-7351","author":"Reddy Pradyumna","key":"e_1_3_2_1_36_1","unstructured":"Pradyumna Reddy, Michael Gharbi, Michal Lukac, and Niloy J. Mitra. 2021. Im2Vec: Synthesizing Vector Graphics Without Vector Supervision. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 7342-7351."},{"key":"e_1_3_2_1_37_1","unstructured":"Machel Reid Nikolay Savinov Denis Teplyashin Dmitry Lepikhin Timothy Lillicrap Jean-baptiste Alayrac Radu Soricut Angeliki Lazaridou Orhan Firat Julian Schrittwieser et al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_1_38_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_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Juan A. Rodriguez Abhay Puri Shubham Agarwal Issam H. Laradji Pau Rodriguez Sai Rajeswar David Vazquez Christopher Pal and Marco Pedersoli. 2024. StarVector: Generating Scalable Vector Graphics Code from Images and Text. arXiv:2312.11556 [cs.CV] https:\/\/arxiv.org\/abs\/2312.11556","DOI":"10.1109\/CVPR52734.2025.01508"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671633"},{"key":"e_1_3_2_1_42_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","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., 2023a. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_43_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023b. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01188"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618364"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00435"},{"key":"e_1_3_2_1_48_1","unstructured":"Yiying Yang Wei Cheng Sijin Chen Xianfang Zeng Fukun Yin Jiaxu Zhang Liao Wang Gang Yu Xingjun Ma and Yu-Gang Jiang. 2025. OmniSVG: A Unified Scalable Vector Graphics Generation Model. arXiv:2504.06263 [cs.CV] https:\/\/arxiv.org\/abs\/2504.06263"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola Alexei A. Efros Eli Shechtman and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. arXiv:1801.03924 [cs.CV] https:\/\/arxiv.org\/abs\/1801.03924","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02085"},{"key":"e_1_3_2_1_52_1","unstructured":"Tianyi Zhang Varsha Kishore Felix Wu Kilian Q. Weinberger and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. arXiv:1904.09675 [cs.CL] https:\/\/arxiv.org\/abs\/1904.09675"},{"key":"e_1_3_2_1_53_1","first-page":"115146","volume-title":"Zhang (Eds.)","volume":"37","author":"Zhao Henry Hengyuan","year":"2024","unstructured":"Henry Hengyuan Zhao, Pan Zhou, Difei Gao, Zechen Bai, and Mike Zheng Shou. 2024. LOVA3: Learning to Visual Question Answering, Asking and Assessment. In Advances in Neural Information Processing Systems, A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Eds.), Vol. 37. Curran Associates, Inc., 115146-115175. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/d0822540916cd716add52e1846a6e18d-Paper-Conference.pdf"},{"key":"e_1_3_2_1_54_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)."},{"key":"e_1_3_2_1_55_1","volume-title":"VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation. arXiv preprint arXiv:2407.10972","author":"Zou Bocheng","year":"2024","unstructured":"Bocheng Zou, Mu Cai, Jianrui Zhang, and Yong Jae Lee. 2024. VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation. arXiv preprint arXiv:2407.10972 (2024)."}],"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\/3746027.3758269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:00:17Z","timestamp":1765342817000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758269"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":55,"alternative-id":["10.1145\/3746027.3758269","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758269","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"}}]}}