{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:10:29Z","timestamp":1765339829909,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["25ZR1401187"],"award-info":[{"award-number":["25ZR1401187"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755392","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"11004-11012","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5531-0182","authenticated-orcid":false,"given":"Hanqi","family":"Chen","sequence":"first","affiliation":[{"name":"SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2676-1412","authenticated-orcid":false,"given":"Zhongyin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4011-593X","authenticated-orcid":false,"given":"Ye","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1278-5226","authenticated-orcid":false,"given":"Zhujin","family":"Liang","sequence":"additional","affiliation":[{"name":"PhiGent Robotics, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5582-577X","authenticated-orcid":false,"given":"Bingbing","family":"Ni","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","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)."},{"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 Vol. 33 (2020) 1877-1901.","key":"e_1_3_2_1_2_1"},{"key":"e_1_3_2_1_3_1","first-page":"16351","article-title":"Deepsvg: A hierarchical generative network for vector graphics animation","volume":"33","author":"Carlier Alexandre","year":"2020","unstructured":"Alexandre Carlier, Martin Danelljan, Alexandre Alahi, and Radu Timofte. 2020. Deepsvg: A hierarchical generative network for vector graphics animation. Advances in Neural Information Processing Systems, Vol. 33 (2020), 16351-16361.","journal-title":"Advances in Neural Information Processing Systems"},{"unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu et al. 2024. Expanding Performance Boundaries of Open-Source Multimodal Models with Model Data and Test-Time Scaling. arXiv preprint arXiv:2412.05271 (2024).","key":"e_1_3_2_1_4_1"},{"unstructured":"Victor Condino. 2022. Large collection of labelled SVG icon graphics in a variety of styles. https:\/\/www.kaggle.com\/datasets\/victorcondino\/svgicons\/.","key":"e_1_3_2_1_5_1"},{"unstructured":"LMDeploy Contributors. 2023. LMDeploy: A Toolkit for Compressing Deploying and Serving LLM. https:\/\/github.com\/InternLM\/lmdeploy.","key":"e_1_3_2_1_6_1"},{"unstructured":"Vision Cortex. 2023. Raster to Vector Graphics Converter built on top of visioncortex. https:\/\/github.com\/visioncortex\/vtracer.","key":"e_1_3_2_1_7_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_8_1"},{"key":"e_1_3_2_1_9_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","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, Vol. 30 (2017)."},{"key":"e_1_3_2_1_10_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_1_11_1","volume-title":"The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751","author":"Holtzman Ari","year":"2019","unstructured":"Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2019. The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751 (2019)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1109\/CVPR52729.2023.00190"},{"key":"e_1_3_2_1_13_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux.","key":"e_1_3_2_1_14_1"},{"key":"e_1_3_2_1_15_1","article-title":"Differentiable Vector Graphics Rasterization for Editing and Learning","volume":"39","author":"Li Tzu-Mao","year":"2020","unstructured":"Tzu-Mao Li, Michal Luk\u00e1\u010d, Gharbi Micha\u00ebl, and Jonathan Ragan-Kelley. 2020. Differentiable Vector Graphics Rasterization for Editing and Learning. ACM Trans. Graph. (Proc. SIGGRAPH Asia), Vol. 39, 6 (2020), 193:1-193:15.","journal-title":"ACM Trans. Graph. (Proc. SIGGRAPH Asia)"},{"key":"e_1_3_2_1_16_1","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device llm compression and acceleration","volume":"6","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. Awq: Activation-aware weight quantization for on-device llm compression and acceleration. Proceedings of Machine Learning and Systems, Vol. 6 (2024), 87-100.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_17_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892-34916."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1109\/ICCV.2019.00802"},{"key":"e_1_3_2_1_19_1","volume-title":"Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)."},{"key":"e_1_3_2_1_20_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"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."},{"unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9.","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","volume-title":"Starvector: Generating scalable vector graphics code from images. arXiv preprint arXiv:2312.11556","author":"Rodriguez Juan A","year":"2023","unstructured":"Juan A Rodriguez, Shubham Agarwal, Issam H Laradji, Pau Rodriguez, David Vazquez, Christopher Pal, and Marco Pedersoli. 2023. Starvector: Generating scalable vector graphics code from images. arXiv preprint arXiv:2312.11556 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_25_1","volume-title":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer. arXiv preprint arXiv:2502.01105","author":"Song Yiren","year":"2025","unstructured":"Yiren Song, Danze Chen, and Mike Zheng Shou. 2025. LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer. arXiv preprint arXiv:2502.01105 (2025)."},{"unstructured":"SVGRepo. 2016. Open-licensed svg vector and icons. https:\/\/www.svgrepo.com\/.","key":"e_1_3_2_1_26_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.1109\/CVPR.2016.308"},{"unstructured":"Qwen Team. 2024. Qwen2.5: A Party of Foundation Models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/","key":"e_1_3_2_1_28_1"},{"key":"e_1_3_2_1_29_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_30_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, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_31_1","volume-title":"Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models. arXiv preprint arXiv:2411.16602","author":"Wu Ronghuan","year":"2024","unstructured":"Ronghuan Wu, Wanchao Su, and Jing Liao. 2024. Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models. arXiv preprint arXiv:2411.16602 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.1145\/3618364"},{"key":"e_1_3_2_1_33_1","volume-title":"Empowering LLMs to Understand and Generate Complex Vector Graphics. arXiv preprint arXiv:2412.11102","author":"Xing Ximing","year":"2024","unstructured":"Ximing Xing, Juncheng Hu, Guotao Liang, Jing Zhang, Dong Xu, and Qian Yu. 2024a. Empowering LLMs to Understand and Generate Complex Vector Graphics. arXiv preprint arXiv:2412.11102 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1109\/CVPR52733.2024.00435"},{"key":"e_1_3_2_1_35_1","volume-title":"Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923","author":"Zhang Zhuosheng","year":"2023","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2023. Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_36_1","DOI":"10.1109\/CVPR52733.2024.00423"},{"key":"e_1_3_2_1_37_1","volume-title":"Llamafactory: Unified efficient fine-tuning of 100 language models. arXiv preprint arXiv:2403.13372","author":"Zheng Yaowei","year":"2024","unstructured":"Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, Zhangchi Feng, and Yongqiang Ma. 2024. Llamafactory: Unified efficient fine-tuning of 100 language models. arXiv preprint arXiv:2403.13372 (2024)."}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '25","name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:08:57Z","timestamp":1765339737000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755392"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":37,"alternative-id":["10.1145\/3746027.3755392","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755392","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"}}]}}