I'm a 4th year Ph.D. student at Kim Jaechul Graduate School of AI, KAIST, advised by professor Jaegul Choo.

My research interest lies in video generation, world modeling, and 2D/3D vision and graphics. I am passionate about leveraging computer vision systems to address real-world challenges and applications.

Contact

  • sharpeeee [at] kaist.ac.kr

Education

  • Ph.D. Student in Artificial Intelligence

    Sep. 2021 - Present

    Korea Advanced Institute of Science and Technology (KAIST)

    Advisor: Prof. Jaegul Choo

  • BS in School of Computing, Electrical Engineering (Double Major)

    Mar. 2016 - 2021

    Korea Advanced Institute of Science and Technology (KAIST)

Professional Experiences

  • Microsoft Research, Game Intelligence Team
    Jun. 2025 - Sep. 2025

    AI Research Intern
  • NVIDIA, Digital Human Team
    Jun. 2024 - Dec. 2024

    AI Research Intern
  • Naver Cloud, Neural 3D Team
    Feb. 2024 - Jun. 2024

    AI Research Intern
  • Kakao Enterprise, Vision Intelligence Team
    Jul. 2022 - Dec. 2022

    AI Research Intern
  • Mindslab
    Mar. 2021 - Aug. 2021

    AI Research Intern
  • SKT
    Jun. 2019 - Jun. 2020

    AI Fellowship
  • KAKAO, Recommendation Systems Team
    Sep. 2018 - Feb. 2019

    AI Research Intern

Publications

  • ACG: Action Coherence Guidance for Flow-based VLA models

    Minho Park, Kinam Kim, Junha Hyung, Hyojin Jang, Hoiyeong Jin, Jooyeol Yun, Hojoon Lee, Jaegul Choo

    under review

    [ paper ] [ project page ]

  • Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs

    Daehoon Gwak, Minseo Jung, Junwoo Park, Minho Park, ChaeHun Park, Junha Hyung, Jaegul Choo

    The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025

    [ paper ] [ project page ]

  • Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models

    Kinam Kim*, Junha Hyung*, Jaegul Choo (* equal contribution)

    arXiv preprint

    [ paper ] [ project page ]

  • Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling

    Junha Hyung*, Kinam Kim*, Susung Hong, Min-Jung Kim, Jaegul Choo (* equal contribution)

    The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

    [ paper ] [ project page ]

  • SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel-based Head Avatars

    Jaeseong Lee*, Taewoong Kang*, Marcel C. Bühler, Min-Jung Kim,
    Sungwon Hwang, Junha Hyung, Hyojin Jang, Jaegul Choo (* equal contribution)

    The Thirteenth International Conference on Learning Representations (ICLR), 2025

    [ paper ] [ project page ]

  • Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting

    Junha Hyung, Susung Hong, Sungwon Hwang, Jaeseong Lee, Jaegul Choo†, Jin-Hwa Kim† († corresponding authors)

    The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

    [ paper ] [ project page ]

  • SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder

    Jaeseong Lee*, Junha Hyung*, Sohyun Jung, Jaegul Choo (* equal contribution)

    The 18th European Conference on Computer Vision (ECCV), 2024

    [ paper ] [ project page ]

  • Local 3D Editing via 3D Distillation of CLIP Knowledge

    Junha Hyung, Sungwon Hwang, Daejin Kim, Hyunji Lee, Jaegul Choo

    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

    [ paper ] [ project page ]

  • MagiCapture: High-Resolution Multi-Concept Portrait Customization

    Junha Hyung*, Jaeyo Shin*, Jaegul Choo (* equal contribution)

    Association for the Advancement of Artificial Intelligence (AAAI), 2024

    [ paper ] [ project page ]

  • FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields

    Sungwon Hwang, Junha Hyung, Daejin Kim, Min-Jung Kim, Jaegul Choo

    Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023

    [ paper ] [ project page ]

  • PixelHuman: Animatable Neural Radiance Fields from Few Images

    Gyumin Shim, Jaeseong Lee, Junha Hyung, Jaegul Choo

    arXiv preprint

    [ paper ]

  • Text2Control3D: Controllable 3D Avatar Generation in Neural Radiance Fields using Geometry-Guided Text-to-Image Diffusion Model

    Sungwon Hwang, Junha Hyung, Jaegul Choo

    arXiv preprint

    [ paper ]

Awards & Honors

  • Google Cloud Award
    2023

    GCP Research Grant
  • Qualcomm
    2020

    Qualcomm-KAIST Multimodal Emotion Recognition Kaggle 1st Prize
  • KAIST
    2019

    Dean's list