Taehyun Byun

I am Taehyun Byun, a Ph.D. student in the Department of Artificial Intelligence at Korea University. My research centers on achieving fine-grained controllability in generative motion synthesis. By developing frameworks such as conditional motion inbetweening, controllable single motion synthesis, and adaptive Hilbert diffusion models, I aim to bridge the gap between abstract AI representations and physical reality. Leveraging reinforcement learning and human motion retargeting, my work seeks to enable humanoid robots to interpret and manifest the nuances of human movement, effectively translating human-centered data into adaptive, physically-consistent robotic actions.