Xuancheng Xu

Xuancheng Xu

Nanjing University of Posts and Telecommunications

Visit tracker

Hi there! I am a second-year Ph.D. student at Nanjing University of Posts and Telecommunications. My research interests revolve around generative AI and video diffusion models, with a special focus on controllable video generation and video world models.

I am fortunate to be advised by Prof. Bingkun Bao at the Multimedia Cognitive Computing Lab. Together, we explore cutting-edge research in multimedia and artificial intelligence.

If you have any questions about my projects or want to collaborate, feel free to drop me an email at 2024010131@njupt.edu.cn. I’m always happy to connect and share ideas! 💡🤝

🔥 News

  • 🎉February, 2026. Our paper SMRABooth has been accepted to CVPR 2026!
  • 🎉May, 2025. Our paper CLGC has been selected for Oral presentation in ICME 2025!
  • 🎉March, 2025. Our paper CLGC has been accepted to ICME 2025!

📝 Publications

CVPR 2026
sym

SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation
Xuancheng Xu, Yaning Li, Sisi You, Bing-kun Bao

[Paper] [Project page] [Code] GitHub Stars

  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026
  • We explore the application of representation alignment in video customization and demonstrate significant performance improvements across various baselines.
Under Evaluation
sym

Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization
Xuancheng Xu, Gengyun Jia, Bing-kun Bao

[Project page]

  • Under Evaluation.
  • We pioneer the task of multi-concept video customization by systematically categorizing content, style, and motion, and establish a comprehensive benchmark comprising four distinct tasks to evaluate this capability. Furthermore, we introduce a novel framework to effectively disentangle and recombine diverse concepts from data.
ICME 2025 Oral
sym

CLGC: Continuous layout guidance for consistent text-to-video editing
Xuancheng Xu, Ming Tao, Bing-kun Bao

[Paper]

  • IEEE International Conference on Multimedia & Expo (ICME) 2025 [Oral]
  • We propose CLGC, a novel framework that leverages layout guidance for consistent and efficient video editing.

🎖 Honors and Awards

  • 2024.10 The First Prize Scholarship (Top 10%)

📖 Educations

  • 2024.09 - 2029.06 (now), Ph.D., Nanjing University of Posts and Telecommunications, Nanjing, China.
  • 2020.09 - 2024.06, Bachelor of Communication Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China.