cv Download CV

Curriculum Vitae of Taehyun Byun.

General Information

Full Name Taehyun Byun
Affiliation Robot Intelligence Lab. (RILAB), Korea University
Languages Korean, English

Education

  • 2021-Present
    Ph.D. in Artificial Intelligence
    Korea University, Seoul, South Korea
    • Advisor: Professor Sungjoon Choi
  • 2015-2017
    M.S. in Statistics
    Korea University, Seoul, South Korea
    • Advisor: Professor Myoungshic Jhun
  • 2009-2015
    B.S. in Information and Mathematics
    Korea University, Sejong, South Korea

Experience

  • 2020 - 2021
    Founder
    ESTIMO Inc., Korea
    • Founded ESTIMO and developed a rehabilitation and physical therapy application using pose estimation.
  • 2018 - 2019
    Research Scientist
    CONTINUUM Inc., Korea
    • Conducted computer vision research in pose estimation, classification, and detection.

Publications & Presentations

  • 2026
    Robot Motion Transition with Human Motion Prior
    arXiv preprint
  • 2026
    Controllable Single Motion Synthesis
    Pattern Recognition (Revised and resubmitted)
  • 2026
    Adaptive Hilbert Diffusion Models for Controllable Smoothness in Continuous Function Generation
    Computational Visual Media (Accepted)
    • Co-first author (equal contribution)
  • 2026
    CLIP-Actor-X: Text-driven 4D Human Avatar Generation via Cross-modal Synthesis-through-Optimization
    IEEE Transactions on Pattern Analysis and Machine Intelligence
    • Co-first author (equal contribution)
  • 2026
    Effective Evaluation of Exoskeleton Using Exo-Agnostic Uncertainty-Aware Classification Model with Wearable Sensors
    ACM Augmented Humans (AHs) — Poster
  • 2025
    Robust and Expressive Humanoid Motion Retargeting via Optimization-Based Rig Unification
    IEEE/RSJ IROS
  • 2024
    Towards Embedding Dynamic Personas in Interactive Robots: Masquerading Animated Social Kinematic (MASK)
    IEEE Robotics and Automation Letters
  • 2023
    Score-based Generative Modeling through Stochastic Evolution Equations in Hilbert Spaces
    Advances in Neural Information Processing Systems (NeurIPS)
  • 2022
    Learning Joint Representation of Human Motion and Language
    arXiv preprint
  • 2022
    Conditional Motion In-Betweening
    Pattern Recognition
  • 2017
    A Study of Correlation Curves Estimation
    Journal of The Korean Data Analysis Society

Academic Interests

  • Human-Grounded Humanoid Motion Synthesis
    • Human Motion Priors for Humanoid Motion Generation
    • Spatio-Temporal Alignment & Motion Transitions
  • Generative Modeling & Controllable Motion Synthesis
    • Diffusion Models & Flow Matching
    • Learning Human Motion Distributions & Motion Priors
    • Continuous & Function Space Modeling (Hilbert space-based approaches)
    • Conditional Motion Generation
  • Human-Robot Interaction & Humanoid Control
    • Fine-grained Controllability & Motion Priors
    • Human-to-Humanoid Motion Retargeting
    • Controllable Motion In-betweening