Changyeon Kim

changyeon.kim [AT] kaist.ac.kr

changyeon.jpg

Hello. I am a PhD student at KAIST, advised by Jinwoo Shin and Kimin Lee, and a visiting PhD student at UT Austin advised by Yuke Zhu. I also worked closely with Honglak Lee at UMich and Joseph J. Lim at KAIST.

My research centers on training artificial agents to align with human intents, even when explicit reward signals are limited or unavailable. I focus on developing algorithms that derive suitable reward functions from real human preferences or foundational vision-language models, which encapsulate extensive human knowledge. Beyond this primary theme, I also explore broader decision-making challenges, including (M)LLM-based agents, offline reinforcement learning, and generalization of RL solutions across diverse environments.

Prior to my graduate studies, I was a machine learning engineer at Recommendation Team of Kakao. Before that, I completed my BS in Computer Science at KAIST.


News

Sep 22, 2023 ARP has been accepted to NeurIPS 2023. See you in New Orleans :us:!
Jun 19, 2023 I will attend ICML 2023 in person for presenting workshop paper (ARP). Feel free to contact to meet or chat in Hawaii, USA :us:.
Jan 21, 2023 Preference Transformer is accepted to ICLR2023 :smile:. Hope to see you in Kigali, Rwanda :rwanda:!

Publications

  1. CoRLW
    Subtask-Aware Visual Reward Learning from Segmented Demonstrations
    Changyeon Kim, Minho Heo, Doohyun Lee, Jinwoo Shin, Honglak Lee, Kimin Lee, and Joseph J. Lim
    In CoRL 2024 Workshop on Mastering Robot Manipulation in a World of Abundant Data, 2024
    PDF
  2. ICLRWSpotlight
    B-MoCA: Benchmarking Mobile Device Control Agents across Diverse Configurations
    Juyong Lee, Minyong An, Taywon Min,  Changyeon Kim, and Kimin Lee
    In International Conference on Learning Representations (ICLR) Workshop on Generative Models for Decision Making, 2024
    Spotlight Presentation
    arXiv Code Website
  3. NeurIPS
    Guide Your Agent with Adaptive Multimodal Rewards
    Changyeon Kim, Younggyo Seo, Hao Liu, Lisa Lee, Jinwoo Shin, Honglak Lee, and Kimin Lee
    In Conference on Neural Information Processing Systems (NeurIPS), 2023
    Previously accepted to ICML 2023 Workshop on New Frontiers in Learning, Control, and Dynamical Systems
    Finalist of Qualcomm Innovation Fellowship 2024 Korea
    arXiv PDF Code Website
  4. ICLR
    Preference Transformer: Modeling Human Preferences using Transformers for RL
    Changyeon Kim*, Jongjin Park*, Jinwoo Shin, Honglak Lee, Pieter Abbeel, and Kimin Lee
    In International Conference on Learning Representations (ICLR), 2023
    (*: equal contribution)
    arXiv PDF Code Website
  5. NeurIPSW
    Dynamics-Augmented Decision Transformer for Offline Dynamics Generalization
    Changyeon Kim*, Junsu Kim*, Younggyo Seo, Kimin Lee, Honglak Lee, and Jinwoo Shin
    In Conference on Neural Information Processing Systems (NeurIPS) Workshop on Offline Reinforcement Learning, 2022
    (*: equal contribution)
    PDF

Work Experience


Recommendation Team, Kakao
Machine Learning Engineer (Dec 2020 ~ Feb 2022)

Data Science Group, Institute of Basic Science
Resarch Intern advised by Prof. Meeyoung Cha (Jul 2019 - Nov 2020)


Honors and Awards

Finalist,  Qualcomm Innovation Fellowship 2024 Korea
Travel Award ($2,000),  Conference on Neural Information Processing Systems (NeurIPS), 2023
Recipient ($3,000),  KAIST-Google Partnership Program, 2023
Recipient ($2,000),  Google East Asia Student Travel Grant, 2023
Travel Award ($1,000),  International Conference on Learning Representations (ICLR), 2023
Dean's List,  KAIST Department of Engineering, 2019
Recipient ($5,000),  Line Scholarship, 2019
Recipient,  National Science and Engineering Scholarship, Korea Ministry of Science and ICT, 2017 - 2019
Recipient ($3,000),  Kwanjeong Scholarship, 2017


Invited Talks

Guide Your Agent with Adaptive Multimodal Rewards
LG AI Research (New Orleans, LA, USA)


Academic Services

Conference Reviewer:  ICML (2024), NeurIPS (2024)
Workshop Reviewer:  Frontiers4LCD@ICML'23