Juyong Lee

I am a master student in the Cognitive Learning for Vision and Robotics (CLVR) Lab at KAIST, advised by Joseph Lim. I received B.S. degree by double majoring both Computer Science and Engineering & Mathematics at POSTECH, where I could fortunately work with Dongwoo Kim, Jaesik Park, and Wankyun Chung.

CV  /  Google Scholar  /  Email

profile photo
Research

I'm interested in understanding the fundamental principles of intelligence and building AI for invention. My research interests lie in domain generalization, structured representation learning, and deep generative models. Currently, I am working on the method of helping AI agents to understand a structure of its behaviors and to generate its own objectives. I hope the machine for invention being used for making universe exploring robots, creating the time machine, and dealing with all matters! :)

GM-VAE: Representation Learning with VAE on Gaussian Manifold
Seunghyuk Cho, Juyong Lee, Dongwoo Kim
JKAIA (Awarded), 2022
paper

From the observation that the set of the diagonal Gaussian distributions with the Fisher information metric forms a product hyperbolic space (we name Gaussian manifold), we propose a variational auto-encoder whose latent space is the Gaussian manifold.

A Rotated Hyperbolic Wrapped Normal Distribution for Hierarchical Representation Learning
Seunghyuk Cho, Juyong Lee, Jaesik Park, Dongwoo Kim
NeurIPS, 2022
paper / code

A simple yet effective alteration of a hyperbolic wrapped normal distribution (HWN), to better utilize the geometric properties of the diagonal HWN. We analyze the geometric properties of the diagonal HWN and alleviate the limitation by introducing the rotated hyperbolic wrapped normal distribution (RoWN).

Style-Agnostic Reinforcement Learning
Juyong Lee, Seokjun Ahn, Jaesik Park
ECCV, 2022
paper / code

Style-agnostic reinforcement learning algorithm, with the aim of both neural style transfer and adversarial learning. The style, here, refers to task-irrelevant details in the image, such as the background color. We let agents to learn style-agnostic representation by generating adversarial perturbation in the latent space and to show generalized performances.

A 3D cell printed muscle construct with tissue-derived bioink for the treatment of volumetric muscle loss
Yeong-Jin Choi, Young-Joon Jun, DongYeon Kim, Hee-Gyeong Yi, Su-Hun Chae, Junsu Kang, Juyong Lee, Ge Gao, Jeong-Sik Kong, Jinah Jang, Wan Kyun Chung, Jong-Won Rhie, Dong-Woo Cho
Biomaterials, 2019
paper

A novel treatment for volumetric muscle loss with decellularized extraceullar matrix bioink using 3D cell printing technology. I, especially, participated in situ functional analysis of the 3D printed muscle cell, to electrically stimulate the peroneal nerve of mice legs. The results verifies that a 3D cell printing approach could effectively generate biomimetic engineered muscles to improve the treatment.


The source code is from here