Junming Huang - 黄俊铭
I am a Ph.D. student at the State Key Lab of CAD&CG, Zhejiang University, under the supervision of Prof. Weiwei Xu. Prior to this, I received my B.E. degree from the School of Software at Yunnan University. My primary research interests lie in Generative Models(including MLLMs and Diffusion Models), Computer Graphics, and Embodied AI.
Email: junminghuang [AT] zju.edu.cn
News
- May 2026: 🎉 CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models was accepted to ICML 2026.
- Nov 2025: 🎉 VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework was accepted as an Oral paper at WACV 2026. The oral presentation is available on YouTube.
- May 2025: 🎉 Physically Based Facial Texture Generation in the Wild was accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2025.
- Apr 2025: 🎉 BuildingBlock: A Hybrid Approach for Structured Building Generation was accepted to ACM SIGGRAPH 2025. The oral presentation is available on YouTube.
Publications
Physically Based Facial Texture Generation in the Wild
IEEE Transactions on Pattern Analysis and Machine Intelligence 2025
Industry Experience
Research Intern (Computer Graphics, 3D Generation) @ Tencent
Apr 2024 - Present- Developed a diffusion model-guided method for structured building generation using procedural content generation (PCG).
- A paper accepted by SIGGRAPH 2025.
- Developed a Unified MLLM for 3D understanding and generation.
- A paper accepted by ICML 2026.
Research Intern (Computer Graphics, Digital Human Generation) @ Kuaishou
Apr 2023 - Apr 2024- Led the research and development of a text-driven facial material generation method.
- A paper accepted by TPAMI and one national invention patent.