Junsu Kim

About

I am a Team Lead of Learning-based Robot Control at Diden Robotics, where I am developing gait algorithms for quadruped and humanoid robots for industrial applications. I received my Ph.D. in Artificial Intelligence from Korea Advanced Institute of Science and Technology (KAIST) in Aug. 2025, where I was advised by Prof. Jinwoo Shin and Prof. Kimin Lee at ALIN Lab. During my Ph.D., I was a visiting student at UC Berkeley, advised by Prof. Sergey Levine. Previously, I received B.S in Electrical Engineering from KAIST in Feb. 2020. During my graduate studies, my research focused on solving challenging decision-making problems via RL (e.g., long-horizon tasks, robotic manipulation), with particular emphasis on hierarchical RL and representation learning. I have also worked on various areas of reinforcement learning including goal-conditioned RL, model-based RL, and multi-agent RL, as well as machine learning for drug discovery.

Topics of interest

Deep Reinforcement Learning: arXiv'24, NeurIPS'24, ICML'23, ICLR'23, NeurIPSW'22, ICML'22, NeurIPS'21
Representation learning for Reinforcement Learning ICML'24, ICML'23
Machine Learning for Drug Discovery: TMLR'24, ICML'21, NeurIPS'20

Publications

(*: Equal contribution, C: Conferences, J: Journal, W: Workshop, P: preprint).

[P1] Unsupervised-to-Online Reinforcement Learning

Junsu Kim*, Seohong Park*, Sergey Levine

Preprint

Paper

[C8] Binary-Feedback Active Test-Time Adaptation

Taeckyung Lee, Sorn Chottananurak, Junsu Kim, Jinwoo Shin, Taesik Gong, Sung-Ju Lee

International Conference on Machine Learning (ICML), 2025

[C7] Visual Representation Learning with Stochastic Frame Prediction

Huiwon Jang, Dongyoung Kim, Junsu Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo

International Conference on Machine Learning (ICML), 2024

Paper Code Website

[C6] Multi-View Masked World Models for Visual Robotic Manipulation

Younggyo Seo*, Junsu Kim*, Stephen James, Kimin Lee, Jinwoo Shin, Pieter Abbeel

International Conference on Machine Learning (ICML), 2023

RSS Workshop on Experiment-oriented Locomotion and Manipulation Research, 2023 (Spotlight Presentation)

Paper Code Website

[J1] Holistic Molecular Representation Learning via Multi-view Fragmentation

Seojin Kim*, Jaehyun Nam*, Junsu Kim, Hankook Lee, Sungsoo Ahn, Jinwoo Shin

Transactions on Machine Learning Research (TMLR), 2024

ICLR Workshop on Machine Learning for Materials, 2023

Paper

[C5] Imitating Graph-Based Planning with Goal-Conditioned Policies

Junsu Kim, Younggyo Seo, Sungsoo Ahn, Kyunghwan Son, Jinwoo Shin

International Conference on Learning Representations (ICLR), 2023

Paper Code

[W1] Dynamics-Augmented Decision Transformer for Offline Dynamics Generalization

Changyeon Kim*, Junsu Kim*, Younggyo Seo, Kimin Lee, Honglak Lee, Jinwoo Shin

NeurIPS Workshop on Offline Reinforcement Learning, 2022

Paper

[C4] Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning

Kyunghwan Son, Junsu Kim, Sungsoo Ahn, Roben Delos Reyes, Yung Yi, Jinwoo Shin

International Conference on Machine Learning (ICML), 2022

Paper

[C3] Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning

Junsu Kim, Younggyo Seo, Jinwoo Shin

Neural Information Processing Systems (NeurIPS), 2021

Paper Slides Poster Code

[C2] Self-Improved Retrosynthetic Planning

Junsu Kim, Sungsoo Ahn, Hankook Lee, Jinwoo Shin

International Conference on Machine Learning (ICML), 2021

Paper Slides Poster Code

[C1] Guiding Deep Molecular Optimization with Genetic Exploration

Sungsoo Ahn, Junsu Kim, Hankook Lee, Jinwoo Shin

Neural Information Processing Systems (NeurIPS), 2020

Paper Code

Education

Korea Advanced Institute of Science and Technology (KAIST)Mar. 2020 - present

M.S./Ph.D. in Artificial Intelligence

Korea Advanced Institute of Science and Technology (KAIST)Mar. 2015 - Feb. 2020

B.S. in Electrical Engineering (Summa Cum Laude)

Honors & Awards

Finalist, Qualcomm Innovation Fellowship Korea

Qualcomm, 2022

NAVER Best Paper Award

Korean Artificial Intelligence Association, 2021

Finalist, Qualcomm Innovation Fellowship Korea

Qualcomm, 2021

KT Prize, Post Corona AI Challenge: Infectious Disease Modelling

Korea Ministry of Science and ICT, National IT Industry Promotion Agency (NIPA), and KT, 2020

Qualcomm-KAIST Innovation Award

Qualcomm and KAIST, 2018

National Science and Engineering Undergraduate Scholarship

Korea Ministry of Science and ICT, 2017-2018

Invited Talks

Unsupervised-to-Online Reinforcement Learning

Hyundai Motor Group, Oct 2024

Guiding Deep Molecular Optimization with Genetic Exploration

GC Biopharma, Aug 2023

Combining Handcrafted Search Algorithms with Deep Reinforcement Learning

Pohang University of Science and Technology (POSTECH), Jun. 2022

Academic Services

Conference Reviewer

Neural Information Processing Systems (NeurIPS)
International Conference on Machine Learning (ICML)
International Conference on Learning Representations (ICLR)
IEEE International Conference on Robotics and Automation (ICRA)
Conference on Robot Learning (CoRL)

Vitæ

Full CV in PDF (Last update: Oct 2024).

Diden Robotics Jul. 2025 - present

Team Lead, Learning-based Robot Control
UC Berkeley Feb. 2024 - Jul. 2024

Visiting Student (Advisor: Sergey Levine)
KAIST Mar. 2020 - Aug. 2025

M.S./Ph.D. in Artifical Intelligence
AIZEN global Mar. 2018 - Aug. 2018

Intern, Deep Learning for Financial Service
SK Hynix Jun. 2017 - Jul. 2017

Intern, DRAM Computing Core Design
National University of Singapore Jan, 2017 - May. 2017

Visiting Student
KAIST Mar, 2015 - Feb. 2020

B.S. in Electrical Engineering