Hello! I am a researcher working with Professor Honglak Lee at LG AI Research Center, Ann Arbor. Before that, I received my PhD in Computer Science and Engineering at Seoul National University and worked as a member of Vision & Learning Lab.
My research interests mainly lie in LLM and multimodal agents for decision-making in challenging, real-world tasks by leveraging large-scale data and knowledge in foundation models.
Education
- Seoul National University (SNU) (Mar. 2018 - Aug. 2023)
- M.S./Ph.D. in Computer Science and Engineering
- Advisor: Professor Gunhee Kim and Professor Hyun Oh Song
- Korea Advanced Institute of Science and Technology (KAIST) (Feb. 2010 - Jun. 2017)
- B.S. in Computer Science
- Graduated summa cum laude
Publications
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] | |
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 (*equal contribution) 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 (*equal contribution) ICML 2021 [paper] [appx] [arxiv] [talk] [code] | |
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) [paper] [appx] [talk] [code] | |
EMI: Exploration with Mutual Information Hyoungseok Kim*, Jaekyeom Kim*, Yeonwoo Jeong, Sergey Levine, Hyun Oh Song (*equal contribution) ICML 2019 (Long talk) [paper] [supp] [arxiv] [talk] [code] |
Honors & Awards
- Best PhD Dissertation Award (Aug. 2023, Dept. of Computer Science and Engineering, Seoul National University)
- Star Student Researcher Award (Feb. 2023, Brain Korea (BK21) FOUR Intelligence Computing, Seoul National University)
- Youlchon AI Star Fellowship (Jul. 2022, Youlchon Foundation)
- Naver PhD Fellowship (Dec. 2021, Naver)
- Google PhD Fellowship - Area: Machine Learning (Sep. 2021, Google)
- Samsung Humantech Paper Award - Silver Prize in Signal Processing (Feb. 2021, Samsung Electronics)
- Qualcomm Innovation Fellowship Korea (Dec. 2020, Qualcomm AI Research)
- On-Dream Outstanding Scholar Award (Dec. 2020, Hyundai Motor Chung Mong-Koo Foundation)
- On-Dream Future Talent Graduate Scholarship (Jul. 2020, Hyundai Motor Chung Mong-Koo Foundation)
- Kwanjeong Domestic Scholarship (Apr. 2018, Kwanjeong Educational Foundation)
- Summa Cum Laude Honor (Feb. 2018, Korea Advanced Institute of Science and Technology)