← Home

Publications

Manuscripts

  1. ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models

    Changyeon Kim, Kimin Lee, Yashraj Narang, and Yijie Guo

    Manuscript, 2026

    Under review at ICRA 2027

    Website

2026

  1. RACE: Calibrated Cumulative Scoring for Rollout-Free Checkpoint Selection

    Changyeon Kim, Yekyung Nah, and Kimin Lee

    NeurIPS 2026 Robot Learning Workshop

    Under review at ICRA 2027

    PDF Website

  2. Trust Region Q Adjoint Matching

    Yonghoon Dong, Kyungmin Lee, Changyeon Kim, Jaehyuk Kim, and Jinwoo Shin

    Conference on Neural Information Processing Systems (NeurIPS), 2026

    arXiv

  3. Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

    Huihan Liu, Changyeon Kim, Bo Liu, Minghuan Liu, and Yuke Zhu

    International Conference on Machine Learning (ICML), 2026

    Oral Presentation (168 / 23918 = 0.7%)

    arXiv Code Website

  4. Contrastive Representation Regularization for Vision-Language-Action Models

    Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, and Jinwoo Shin

    International Conference on Machine Learning (ICML), 2026

    arXiv

  5. Learning Multi-View Spatial Reasoning from Cross-View Relations

    Suchae Jeong*, Jaehwi Song*, Haeone Lee, Hanna Kim, Jian Kim, Dongjun Lee, Dong Kyu Shin, Changyeon Kim, Dongyoon Hahm, Woogyeol Jin, Juheon Choi, and Kimin Lee

    Conference on Computer Vision and Pattern Recognition (CVPR), 2026

    (*: equal contribution)

    OpenReview

  6. DEAS: DEtached value learning with Action Sequence for Scalable Offline RL

    Changyeon Kim, Haeone Lee, Younggyo Seo, Kimin Lee^, and Yuke Zhu^

    International Conference on Learning Representations (ICLR), 2026

    (^: equal advising)

    arXiv PDF Website

  7. Verifier-free Test-Time Sampling for Vision Language Action Models

    Suhyeok Jang, Dongyoung Kim, Changyeon Kim, Youngsuk Kim, and Jinwoo Shin

    International Conference on Learning Representations (ICLR), 2026

    arXiv

  8. HAMLET: Switch Your Vision-Language-Action Model into a History-Aware Policy

    Myungkyu Koo, Daewon Choi, Taeyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, and Jinwoo Shin

    International Conference on Learning Representations (ICLR), 2026

    arXiv Website

2025

  1. B-MoCA: Benchmarking Mobile Device Control Agents across Diverse Configurations

    Juyong Lee, Taywon Min, Minyong An, Dongyoon Hahm, Haeone Lee, Changyeon Kim, and Kimin Lee

    Conference on Lifelong Learning Agents (CoLLAs), 2025

    Previously accepted to ICLR 2024 Generative Models for Decision Making Workshop as a spotlight presentation

    arXiv Code Website

  2. Subtask-Aware Visual Reward Learning from Segmented Demonstrations

    Changyeon Kim, Minho Heo, Doohyun Lee, Jinwoo Shin, Honglak Lee, Joseph J. Lim^, and Kimin Lee^

    International Conference on Learning Representations (ICLR), 2025

    (^: equal advising)

    arXiv PDF Code Website

2023

  1. Guide Your Agent with Adaptive Multimodal Rewards

    Changyeon Kim, Younggyo Seo, Hao Liu, Lisa Lee, Jinwoo Shin, Honglak Lee, and Kimin Lee

    Conference on Neural Information Processing Systems (NeurIPS), 2023

    Previously accepted to ICML 2023 New Frontiers in Learning, Control, and Dynamical Systems Workshop

    Finalist of Qualcomm Innovation Fellowship 2024 Korea

    arXiv PDF Code Website

  2. Preference Transformer: Modeling Human Preferences using Transformers for RL

    Changyeon Kim*, Jongjin Park*, Jinwoo Shin, Honglak Lee, Pieter Abbeel, and Kimin Lee

    International Conference on Learning Representations (ICLR), 2023

    (*: equal contribution)

    arXiv PDF Code Website OpenReview

2022

  1. Dynamics-Augmented Decision Transformer for Offline Dynamics Generalization

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

    NeurIPS 2022 Offline Reinforcement Learning Workshop

    (*: equal contribution)

    PDF OpenReview

Other publications

  1. Moi-mixer: Improving mlp-mixer with multi order interactions in sequential recommendation

    Hojoon Lee, Dongyoon Hwang, Sunghwan Hong, Changyeon Kim, Seungryong Kim, and Jaegul Choo

    ArXiv preprint, 2021

    arXiv

  2. Collecting the public perception of AI and robot rights

    Gabriel Lima, Changyeon Kim, Seungho Ryu, Chihyung Jeon, and Meeyoung Cha

    Proceedings of the ACM on Human-Computer Interaction, 4(CSCW2), pp. 1–24, 2020

    arXiv HTML

BibTeX: Publications · Other publications