Seungjun Moon

Google Scholar / LinkedIn / github

I focus on developing real-time generative models for image and video, advancing model performance through large-scale (>10TB) multi-modal and 3D datasets while optimizing architectures for efficient on-device and real-time inference. My work spans human video generation leveraging large-scale 3D data, and is now expanding toward training Vision–Language–Action (VLA) models for dexterous robotic manipulation, bridging human motion understanding and embodied robot control.

I earned my Master’s degree at KAIST under the supervision of Prof. Jinwoo Shin, following a Bachelor's degree in Electrical Engineering with a minor in Mathematical Sciences, also at KAIST.