Haeone Lee

haeone.lee@kaist.ac.kr

prof_pic.jpg

📍 Seoul, Korea

I am a master student in KAIST Graduate school of AI, advised by Prof. Kimin Lee.

I am interested in robot learning. My aim is to efficiently scale robot learning. Relevant topics include data curation, cross-embodiment learning with universal action spaces, and test-time adaptation.

2026

  1. Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning
    Haeone Lee, Taywon Min, Junsu Kim, Singjae Kang, Fangchen Liu, Lerrel Pinto, and Kimin Lee
    ICRA 2026
  2. 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
    CVPR 2026
  3. DEAS: DEtached value learning with Action Sequence for Scalable Offline RL
    Changyeon Kim, Haeone Lee, Younggyo Seo, Kimin Lee, and Yuke Zhu
    ICLR 2026
    HTML

2025

  1. Understanding Impact of Human Feedback via Influence Functions
    Taywon Min, Haeone Lee, Yongchan Kwon, and Kimin Lee
    ACL 2025 (Main)
    HTML

2024

  1. Benchmarking Mobile Device Control Agents across Diverse Configurations
    Juyong Lee, Taywon Min, Minyong An, Dongyoon Hahm, Haeone Lee, Changyeon Kim, and Kimin Lee
    CoLLAs 2025
    HTML