Ximing Xing is a Ph.D. student (2022-Present) in Software Engineering at Beihang University, advised by Professor Qian Yu. He is currently a research intern at Tencent Hunyuan, working on multimodal vector graphics large language models.

He is dedicated to advancing the frontiers of AI-driven content creation, with a particular focus on the generation and understanding of vector graphics. His research spans deep generative models, vector art synthesis, text-to-SVG generation, neural rendering, SVG diffusion models, and multimodal SVG LLMs.

His groundbreaking work has been published in top-tier venues including CVPR’24/25, T-PAMI’25, and NeurIPS’23, with his T-PAMI paper being the first SVG generation work ever published in this prestigious journal. Some of his representative works include:

Impact & Open Science: His commitment to open science and reproducible research is reflected in his highly influential open-source projects, which have collectively garnered substantial community adoption on GitHub. github

Beyond academic publications, he actively contributes to the broader AI community through large-scale datasets, production-ready code libraries, and interactive demos on HuggingFace (@xingxm profile, SVGRender Space), making cutting-edge vector graphics research accessible to researchers and practitioners worldwide.

🔥 News

  • 2025.02:  🎉🎉 Our paper LLM4SVG has been accepted by CVPR 2025!
  • 2025.02:  🎉🎉 Our paper SVGDreamer++ has been accepted by T-PAMI! This is the first paper on SVG generation ever published in T-PAMI.
  • 2024.02:  🎉🎉 Our paper SVGDreamer has been accepted by CVPR 2024!
  • 2023.12:  🎉🎉 We released PyTorch-SVGRender, a state-of-the-art library for differentiable SVG rendering in PyTorch.

📝 Publications

🏷️ Topic: Vector Graphics Synthesis

ArXiv
ReasonSVG

Reason-SVG: Hybrid Reward RL for Aha-Moments in Vector Graphics Generation

Ximing Xing, Yandong Guan, Jing Zhang, Dong Xu, Qian Yu

TL;DR: Reason-SVG introduces the first framework to enhance SVG generation in LLMs through a “Drawing-with-Thought” (DwT) paradigm—combining explicit design reasoning with code—trained via supervised fine-tuning and HyperReward-driven reinforcement learning.

CVPR 2025
LLM4SVG

Empowering LLMs to Understand and Generate Complex Vector Graphics

Ximing Xing, Juncheng Hu, Guotao Liang, Jing Zhang, Dong Xu, Qian Yu

project dataset

TL;DR: LLM4SVG introduces learnable SVG Semantic Tokens and a large SVGX-SFT dataset, enabling LLMs to understand and generate complex vector graphics.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR'25)

Project | Code | SVGX-SFT-1M Dataset

T-PAMI 2025
SVGDreamer++

SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation

Ximing Xing, Qian Yu, Chuang Wang, Haitao Zhou, Jing Zhang, Dong Xu

project

TL;DR: SVGDreamer++ is an advanced text-to-SVG generator with two core innovations: Hierarchical Image Vectorization (HIVE) - enables semantic object-level and component-level image vectorization, and Adaptive Vector Primitive Control – dynamically assigns the optimal number of vector primitives, capturing fine-grained details without wasting computation.

IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI 2025)

Project | Code | Blog

arXiv 2024
SVGFusion

SVGFusion: Scalable Text-to-SVG Generation via Vector Space Diffusion

Ximing Xing, Juncheng Hu, Jing Zhang, Dong Xu, Qian Yu

project dataset

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 | Code | SVGX-Core-250k Dataset

CVPR 2024
SVGDreamer

SVGDreamer: Text Guided SVG Generation with Diffusion Model

Ximing Xing, Chuang Wang, Haitao Zhou, Jing Zhang, Dong Xu, Qian Yu

project

TL;DR: SVGDreamer introduces Semantic-driven Image VEctorization (SIVE) and Vector Particle-based Score Distillation (VPSD) to generate editable, high-quality SVGs with better shape control and diversity.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR'24)

Project | Code | Blog

ICME 2025
VectorPainter

VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors

Juncheng Hu, Ximing Xing, Jing Zhang, Qian Yu

project

TL;DR: VectorPainter synthesizes text-guided vector graphics by imitating stylized strokes.

IEEE International Conference on Multimedia & Expo (ICME'25)

Project | Code

NIPS 2023
DiffSketcher

DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models

Ximing Xing, Chuang Wang, Haitao Zhou, Jing Zhang, Qian Yu, Dong Xu

project

TL;DR: DiffSketcher pioneered the use of diffusion models for text-to-vector sketch generation.

Advances in Neural Information Processing Systems (NeurIPS'23)

Project | Code

🏷 Topic: CAD Generation

arXiv
Inversion-By-Inversion

CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward

Yandong Guan, Xilin Wang, Ximing Xing, Jing Zhang, Dong Xu, Qian Yu

TL;DR: CAD-Coder enables LLMs to generate complex, valid 3D CAD models from text by outputting CadQuery (Python) scripts, using a novel two-stage training and chain-of-thought approach.

🏷 Topic: Controllable Text-to-Image Generation

arXiv
Inversion-By-Inversion

Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Training

Ximing Xing, Chuang Wang, Haitao Zhou, Zhihao Hu, Chongxuan Li, Dong Xu, Qian Yu

project

TL;DR: Free training for sketch control image synthesis via Stochastic Differential Equations (SDEs).

Project | Code

🏷 Topic: Robust Machine Learning

CVPR 2021
DualGraph

A Graph-Based Method for Reasoning About Label Noise

HaiYang Zhang, Ximing Xing, Liang Liu

TL;DR: DualGraph, the first method for label noise processing based on graph neural networks.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR'21)

📒 Projects

open source
PyTorch-SVGRender

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 and SVG Editing.

website docs space

🌐 Project | 📁 Code | 🤗 HuggingFace | 📄 Docs

🎖 Honors & Awards

  • 2025.04 Academic Excellence Foundation of BUAA for PhD Students.
  • 2024.12 National Scholarship for Doctoral Students.
  • 2021.12 National Scholarship.

💻 Internships

  • 2025.06 - (present), Tencent Hunyuan, research intern (Qingyun Program). Beijing, China.

    Multimodal Vector Graphics Large Language Models research in multimodal large models.

    • Developing novel approaches for multimodal vector graphics understanding and generation.
    • Advancing the integration of large language models with vector graphics synthesis.
  • 2021.06 - 2021.11, Ant Group, machine learning algorithm intern. HangZhou, China.

    Multi-Turn Task-Oriented Dialogue System based on deep reinforcement learning.

    • Behavior cloning to enhance model cold-start training.
    • Agenda-based User Simulator in RL.
    • Turns- and sessions-level reward design for PPO training.

📑 Professional Activities

Conference Reviewer

  • 2025: AAAI, CVPR, SIGGRAPH, SIGGRAPH Asia, NeurIPS

  • 2024: CVPR, ECCV, NeurIPS, ACM MM

Journal Reviewer

  • Computer Vision & Graphics: International Journal of Computer Vision (IJCV), IEEE Transactions on Visualization and Computer Graphics (T-VCG)

Academic Service

  • Active member of the AI and Computer Vision research community
  • Regular reviewer for top-tier conferences and journals in AI, Computer Vision, and Computer Graphics