Wenbo LI
Chasing curiosity by day, embracing life by default.

WENBWenbo LILI

ๆŽๆ–‡ๅš

Exploring multimodal foundation models, World Models, and AIGC.

Scroll

About

I am a research scientist at Joy Future Academy, where I explore multimodal foundation models, World Models, and AIGC. Prior to this, I was part of the Huawei TopMinds program (ๅคฉๆ‰ๅฐ‘ๅนด).

I earned my Ph.D. in the CSE Department at the Chinese University of Hong Kong in 2023, supervised by Prof. Jiaya Jia. During the doctoral study, my first-author work MAT was selected as a CVPR 2022 Best Paper Finalist. I received my Master's degree in 2019 and Bachelor's degree from the IEEE Pilot Class in 2016 from Shanghai Jiao Tong University.

News

  • One paper accepted at CVPR 2026
  • Three papers accepted at ICLR 2026
  • Five papers accepted at AAAI 2026

Projects

Unified Multimodal Model
JoyAI-Image
Multimodal Agents
JarvisEvo JarvisArt JarvisIR
Image & Video Synthesis
FlashVideo UltraPixel ControlNeXt Video-P2P MAT
Image & Video Restoration
MambaIRv2 ContinuousSR CoSeR UHDM SimpleSR MASA-SR EDT

Honors & Awards

  • Paper Award CVPR 2022 Best Paper Finalist
  • Champion MIPI 2025 Challenge on Deblurring
  • Champion AIM 2019 Challenge on Video Extreme Super-Resolution
  • Champion COCO 2018 Challenge on Keypoint Detection
  • Honor Outstanding Graduate, SJTU
  • Scholarship Academic Excellence Scholarship, SJTU
  • Scholarship Wish Enterprise Scholarship
  • Scholarship Fushou Li Enterprise Scholarship
Research Scientist
Email Me