Hello! I am a Ph.D student at KAIST AI, advised by Jaegul Choo.
My main interest lies in developing humanoid robots for assisting households and providing companionship.
Unlike language or image models, teaching robots complex physical tasks is challenging due to limited human demonstration data.
I believe robots should learn through their own experiences using synthetic data generated by simulators and reinforcement learning (RL).
Thus, my future research aims to develop RL algorithms that scale effectively, solve multiple tasks simultaneously, and transfer efficiently between tasks.
If you want to discuss anything; please feel free to reach me :)
