Juyong Lee

I am a PhD(/MS int.) student at KAIST, advised by Kimin Lee. I received B.S. degree with double-major on both Mathematics and Computer Science/Engineering at POSTECH. I have an experience as an exchange student at Stanford.

I am currently intereseted in building intelligent agent.

CV / Google Scholar / Email

Publications

(*: Equal contribution, J: Journal, C: Conference, W: Workshop, P: Preprint)

	[W2] B-MoCA: Benchmarking Mobile Device Control Agents across Diverse Configurations Juyong Lee, Taywon Min, Minyong An, Changyeon Kim, Kimin Lee ICLR 2024 workshop GenAI4DM (spotlight) project / paper / code B-MoCA can serve as a unified testbed for mobile device control agents on performing practical daily tasks across diverse device configurations.
	[W1] LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers Taewook Nam, Juyong Lee, Jesse Zhang, Sung Ju Hwang, Joseph J Lim, Karl Pertsch NeurIPS 2023 workshop ALOE project / paper / code The RL agent discovers semantically meaningful skills with task proposals imagined from a large language model and by getting rewards from a vision-language model.
	[C3] Hyperbolic VAE via Latent Gaussian Distributions Seunghyuk Cho, Juyong Lee, Dongwoo Kim NeurIPS 2023, ICML 2023 workshop TAGML, KAIA 2022 (3rd best paper) paper A newly proposed distribution over a Riemannian manifold of the diagonal Gaussian distributions equipped with Fisher information metric shows high numerical stability.
	[C2] 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) better utilizes the geometric properties of the diagonal HWN.
	[C1] Style-Agnostic Reinforcement Learning Juyong Lee, Seokjun Ahn, Jaesik Park ECCV 2022 paper / code The RL agents become robust to changes in the style of the image (e.g., background color) by adapting on adversarially generated styles.
	[P1] Semi-supervised Image Classification with Grad-CAM Consistency Juyong Lee, Seunghyuk Cho preprint / code The supervised-learning models trained with additional Grad-CAM heatmap matching between an image and an augmented version of it show improved generalization ability.
	[J1] 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 Mice legs treated with 3D-printed cell exhibit desired force production functionality with electrical stimulus.

The source code is from here