Hello! I am a Ph.D student at KAIST AI, advised by Jaegul Choo.
I am interested in reinforcement learning and robotics. My current research is focused on utilizing pre-trained foundational models for visuo-motor control.
Email / Google Scholar / LinkedIn / Github
A VLA observes the scene in the camera frame but acts in the robot frame. Robot-centric pointmaps close this gap by giving every pixel its 3D position in the frame where actions are defined.
A hierarchical VLA framework that guides low-level action policies with 3D trajectory predictions.
A simple yet effective neural network architecture for deep RL in visual continuous control, matching or outperforming state-of-the-art methods across DMC, Adroit, and Meta-World while being more computationally efficient than DrQ-v2.
A skill discovery algorithm that learns diverse behaviors while following the behaviors in "do" videos while avoiding the behaviors in "don't" videos.
A simple add-on module which injects convolutions into pretrained ViTs for Visuo-motor Control.
An unsupervised skill discovery algorithm, which addresses the limited exploration of previous algorithms through explicit guidance.
We present a visual pre-training algorithm grounded in self-predictive learning principles tailored for reinforcement learning.
We construct a real estate appraisal framework that integrates spatial and temporal aspects, validated using a dataset of 3.6M real estate transactions in South Korea from 2016 to 2020.
We gathered data from 280,000 matches played by the top 0.3% rank players in Korea for League of Legends. From this, we developed DraftRec, a personalized champion recommendation system aimed at maximizing players' win rates.
Template based on Jon Barron's website.