I am a Ph.D. student in Software Engineering (M.S.–Ph.D. successive program) at the School of Software, Beihang University, advised by Prof. Qian Yu.
My research lies at the intersection of vector graphics, generative models, and multimodal large language models. I am particularly interested in differentiable SVG rendering, text/image-to-SVG generation, and vector animation, with the goal of building systems that understand, create, and edit structured visual content the way designers do.
🔥 News
- 2026.05: 🎉🎉 Our paper VAnim has been accepted by ICML 2026!
- 2025.07: 🎉🎉 Our paper GroupSketch has been accepted by ACM MM 2025!
- 2025.03: 🎉🎉 Our paper VectorPainter has been accepted by ICME 2025!
- 2025.02: 🎉🎉 Our paper LLM4SVG has been accepted by CVPR 2025!
- 2023.12: 🎉🎉 We released PyTorch-SVGRender, a state-of-the-art library for differentiable SVG rendering in PyTorch.
📝 Publications
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
Guotao Liang, Zhangcheng Wang, Chuang Wang, Juncheng Hu, Haitao Zhou, Junhua Liu, Jing Zhang, Dong Xu, Qian Yu†
TL;DR: VAnim formulates SVG animation as sparse state updates on a persistent DOM tree, combining identification-first motion planning with rendering-aware RL to generate structure-preserving vector animations from text.
International Conference on Machine Learning (ICML), 2026.
Multi-Object Sketch Animation with Grouping and Motion Trajectory Priors
Guotao Liang, Juncheng Hu, Ximing Xing, Jing Zhang, Qian Yu†
TL;DR: GroupSketch synthesizes multi-object sketch animations with grouping and motion trajectory priors, enabling users to create complex animations with ease.
ACM International Conference on Multimedia, 2025.
Empowering LLMs to Understand and Generate Complex Vector Graphics
Ximing Xing, Juncheng Hu, Guotao Liang, Jing Zhang, Dong Xu, Qian Yu†
TL;DR: LLM4SVG introduces learnable SVG Semantic Tokens and a large SVGX-SFT dataset, enabling LLMs to understand and generate complex vector graphics.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
🌐 Project | 📄 Paper | 📁 Code | 🤗 SVGX-SFT-1M Dataset
SVGFusion: Scalable Text-to-SVG Generation via Vector Space Diffusion
Ximing Xing, Juncheng Hu, Jing Zhang, Dong Xu, Qian Yu†
TL;DR: SVGFusion improves text-to-SVG generation by using a VP-VAE to learn a vector representation of SVG elements, and a VS-DiT to generate SVGs from text prompts by performing diffusion within that learned vector space.
🌐 Project | 📄 Paper | 📁 Code ｜ 🤗 SVGX-Core-250k Dataset
VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors
Juncheng Hu, Ximing Xing, Jing Zhang, Qian Yu†
TL;DR: VectorPainter synthesizes text-guided vector graphics by imitating strokes.
IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2025.
📒 Projects
Pytorch-SVGRender: A Differentiable Rendering Library for SVG Creation
👥 Main Contributors: Ximing Xing, Juncheng Hu
TL;DR: SVG Differentiable Rendering: Generating vector graphics using neural networks. Support: text-to-SVG, Image-to-SVG, SVG Editing.
🌐 Project | 📁 Code | 🤗 HuggingFace | 📄 Docs
🎖 Honors and Awards
- 2025.12 Merit Student of Beijing
- 2025.10 National Scholarship for Master’s Students
📖 Educations
-
2024.09 – Present: Ph.D. in Software Engineering (M.S.–Ph.D. Successive Program), School of Software, Beihang University
-
2019.09 – 2024.06: B.S. in Software Engineering, School of Software, Beihang University
- GPA: 3.95730 / 4.00
- Rank: 4 / 187
💻 Internships
-
2024.01 - 2024.06, AISphere, China.
Controllable video generation, Text/Image-to-video generation, video reconstruction using VAE.