VIsual Intelligence and GEneration LAb

Visual Intelligence and Generation Lab

The Visual Intelligence and Generation Lab (VIG Lab) aims to bring innovation to the world by developing Artificial Intelligence based on visual signals. We are pioneering Visual Generative AI that creates and understands complex visual worlds from images and videos to 3D environments. Furthermore, we advance Visual Multimodal AI that empowers systems with cognitive reasoning by synthesizing vision and language. By integrating these multimodal capabilities with generative models, we are dedicated to shaping the future of Physical AI, creating intelligent agents capable of perceiving, reasoning, and acting in the real world.

Specific tasks addressed in our lab

• Visual Generative AI

  • Image / Video /3D Generation

  • Diffusion Models / Flow Matching

  • Gaussian Splatting / NeRF
    
    

• Visual Multimodal AI

  • Large Vision-Language Models (LVLMs)

  • Image / Video Retrieval and Detection

  • Vision-based Dialogue & Reasoning 

 If you are interested in applying for positions (Intern / MS / Ph.D) in our lab, please contact me (sunjaeyoon@cau.ac.kr)