Hello! I am a Researcher in Advanced Agent Lab at LG AI Research (Ann Arbor, Michigan), working with Prof. Honglak Lee. I received my PhD in Computer Science at Seoul National University (advisors: Prof. Gunhee Kim and Prof. Hyun Oh Song).

My research interests mainly lie in building capable AI agents for decision-making in challenging, real-world tasks, with language and multimodal models and reinforcement learning.

Selected Professional Experiences

Publications (*: equal contribution)

Language and Multimodal Models and Agents

Our large-scale analysis with our AI agent suggests that ~80% of the popular datasets with commercially permissive licenses are, in fact, not likely commercially viable due to how those datasets were constructed. Do Not Trust Licenses You See: Dataset Compliance Requires Massive-Scale AI-Powered Lifecycle Tracing
Jaekyeom Kim*, Sungryull Sohn*, Gerrard Jeongwon Jo, Jihoon Choi, Kyunghoon Bae, Hwayoung Lee, Yongmin Park, Honglak Lee
Preprint
[arxiv] [post] [project]
AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
Yao Fu*, Dong-Ki Kim*, Jaekyeom Kim, Sungryull Sohn, Lajanugen Logeswaran, Kyunghoon Bae, Honglak Lee
NeurIPS 2024
[arxiv]
Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents
Jaekyeom Kim, Dong-Ki Kim, Lajanugen Logeswaran, Sungryull Sohn, Honglak Lee
EMNLP 2024 (Findings)
[arxiv] [poster]
SkillAct: Using Skill Abstractions Improves LLM Agents
Anthony Zhe Liu, Jongwook Choi*, Sungryull Sohn, Yao Fu, Jaekyeom Kim, Dong-Ki Kim, Xinhe Wang, Jaewon Yoo, Honglak Lee
ICML 2024 Workshop on LLMs and Cognition
[paper]
Small Language Models Need Strong Verifiers to Self-Correct Reasoning
Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang
ACL 2024 (Findings)
[arxiv]

Reinforcement Learning and Skill Discovery

Constrained GPI for Zero-Shot Transfer in Reinforcement Learning
Jaekyeom Kim, Seohong Park, Gunhee Kim
NeurIPS 2022
[paper] [arxiv] [talk] [code]
Lipschitz-constrained Unsupervised Skill Discovery
Seohong Park, Jongwook Choi*, Jaekyeom Kim*, Honglak Lee Gunhee Kim
ICLR 2022
[paper] [arxiv] [project] [code]
Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods
Seohong Park, Jaekyeom Kim, Gunhee Kim
NeurIPS 2021
[paper] [appx] [arxiv] [talk] [code]
Unsupervised Skill Discovery with Bottleneck Option Learning
Jaekyeom Kim*, Seohong Park*, Gunhee Kim
ICML 2021
[paper] [appx] [arxiv] [talk] [code]
EMI: Exploration with Mutual Information
Hyoungseok Kim*, Jaekyeom Kim*, Yeonwoo Jeong, Sergey Levine, Hyun Oh Song
ICML 2019 (Long talk: top ~4.6%)
[paper] [supp] [arxiv] [talk] [code]

Generalization and Robustness

Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration
Jaekyeom Kim, Minjung Kim, Dongyeon Woo, Gunhee Kim
ICLR 2021
[paper] [arxiv] [talk] [code]
Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot Learning
Jaekyeom Kim, Hyoungseok Kim, Gunhee Kim
ECCV 2020 (Oral: top ~2%)
[paper] [appx] [talk] [code]

Honors & Awards

Education