Zongjian Li
Scholar

Zongjian Li

Google Scholar ID: _TT3r1cAAAAJ
Peking University
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
901
 
H-index
8
 
i10-index
7
 
Publications
9
 
Co-authors
0
 
Contact
GitHubOpen ↗
Publications
3 items
UniWorld-Design: From Pixel Generation to Layer-Native Design
2026
Cited
0
Helios: Real Real-Time Long Video Generation Model
2026
Cited
0
iFSQ: Improving FSQ for Image Generation with 1 Line of Code
2026
Cited
0
Resume
Academic Achievements
  • Published a paper titled 'Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model' at CVPR 2025; Contributed to the open-source community, particularly in the field of video generation technology within AI.
Research Experience
  • Involved in multiple projects including Open-Sora-Plan (aimed at reproducing the Sora model), WF-VAE (research on Video VAE), and UniWorld (high-resolution semantic encoders for unified visual understanding and generation). These projects cover areas such as video generation and image processing.
Education
  • Peking University, Electronic and Computer Engineering
Background
  • Graduated from Peking University in Electronic and Computer Engineering. Interests lie in video and image generation and editing.
Miscellany
  • No specific hobbies or other personal information provided