Yongjae Shin

YongjaeShin.png

I am a Ph.D. student at Smart Information Systems Research Lab (SISReL) in Korea Advanced Institute of Science and Technology (KAIST) advised by Professor Youngchul Sung.

News

Jan 2026 Two papers (FINO, FAC) accepted to ICLR 2026.
May 2025 Two papers (OPT, PARS) accepted to ICML 2025.
Mar 2024 Started an internship at LG AI Research.
Sep 2023 RDE paper accepted to NeurIPS 2023.

Publications (* Equal contribution. † Corresponding authors)

  1. Steer, Refine, and Select: Adapting Generative Policies for Robot Manipulation via Online RL
    Yongjae Shin, Seongmin Kim, Jongseong Chae, Jongeui Park, Jeongwoo Park, and Youngchul Sung
    In Submission
  2. DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning
    Minho Park*, Kinam Kim*, Donghu Kim, Byungkun Lee, Dongyoon Hwang, Yongjae Shin, Junha Hyung, Hojoon Lee†, and Jaegul Choo†
    In Submission
    [project] [code] [dataset]
  3. Adaptive Action Chunking via Multi-Chunk Q Value Estimation
    Yongjae Shin, Jongseong Chae, Seongmin Kim, Jongeui Park, and Youngchul Sung
    NeurIPS 2026 Workshop PTA
    [paper]
  4. Flow Matching with Injected Noise for Offline-to-Online Reinforcement Learning
    Yongjae Shin, Jongseong Chae, Jongeui Park, and Youngchul Sung
    ICLR 2026
    [paper]
  5. Flow Actor-Critic for Offline Reinforcement Learning
    Jongseong Chae, Jongeui Park, Yongjae Shin, Gyeongmin Kim, Seungyul Han, and Youngchul Sung
    ICLR 2026
    [paper]
  6. RL-Studio: A System for Multi-Phase Reinforcement Learning Experimentation
    Whiyoung Jung, Sunghoon Hong, Deunsol Yoon, Jeonghye Kim, Yongjae Shin, Suhyun Jung, Hyundam Yoo, Youngjin Kim, Chanwoo Moon, Woohyung Lim, Soonyoung Lee, and Kanghoon Lee
    AAAI Demonstration 2026
    Work done during an internship at LG AI Research.
    [paper]
  7. Online Pre-Training for Offline-to-Online Reinforcement Learning
    Yongjae Shin, Jeonghye Kim, Whiyoung Jung, Sunghoon Hong, Deunsol Yoon, Youngsoo Jang, Geon-Hyeong Kim, Jongseong Chae, Youngchul Sung, Kanghoon Lee, and Woohyung Lim
    ICML 2025
    Work done during an internship at LG AI Research.
    [paper]
  8. Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data
    Jeonghye Kim, Yongjae Shin, Whiyoung Jung, Sunghoon Hong, Deunsol Yoon, Youngchul Sung, Kanghoon Lee, and Woohyung Lim
    ICML 2025 (Spotlight)
    Work done during an internship at LG AI Research.
    [paper]
  9. Sample-efficient and safe deep reinforcement learning via reset deep ensemble agents
    Woojun Kim*, Yongjae Shin*, Jongeui Park, and Youngchul Sung
    NeurIPS 2023
    [paper]