CV

General Information

Full Name Minguk Kang
Email minguk@pika.art, mingukkang1994@gmail.com
Website mingukkang.github.io
Google Scholar Profile
GitHub MINGUKKANG
X @minguk_kang

Education

  • 02/2020 - 02/2026
    Ph.D. in Graduate School of AI
    Pohang University of Science and Technology (POSTECH), Pohang, Republic of Korea
    • Advisors: Prof. Suha Kwak (2023-2026) and Prof. Jaesik Park (2020-2023)
    • Thesis: Efficient Deep Generative Models for Visual Content Generation
    • GPA: 4.09/4.30
  • 03/2013 - 08/2019
    B.S. in Engineering
    Pusan National University, Busan, Republic of Korea
    • Major: Mechanical Engineering; Minor: Statistics
    • Graduated summa cum laude, ranked 1st among 394 students in the College of Engineering.

Experience

  • 11/2024 - Present
    Founding Research Scientist
    Pika Labs, South Korea (Remote)
    • Core contributor to video generation models, an audio-driven performance model, and PikaStream1.0.
    • Developed tokenizers, distillation pipelines, fast super-resolution methods, and real-time video agent system components.
  • 06/2024 - 10/2024
    Research Scientist Intern
    Pika Labs, Korea (Remote) / Palo Alto, USA
    • Worked with Chenlin Meng on video generation research.
  • 07/2022 - 05/2024
    Research Scientist Intern
    Adobe Research, Korea (Remote) / San Francisco, USA
    • Mentors: Taesung Park, Connelly Barnes, Eli Shechtman, Jun-Yan Zhu, Richard Zhang, Sylvain Paris
    • GigaGAN (CVPR 2023) contributed to the development of Adobe Firefly.
  • 08/2017 - 01/2020
    Undergraduate Research Student
    Vision and Intelligent System Laboratory, Pusan National University
    • Advisor: Prof. Dongjoong Kang

Research Interest

  • Efficient generative AI systems for real-time content generation across video, audio, and multimodal settings.
  • High-compression, low-latency tokenizers, few-step diffusion distillation methods, and fast super-resolution pipelines for interactive generation.
  • Scalable training of GANs and diffusion models, tokenizer design and diffusibility, and multimodal generative modeling.

Selected Awards

  • Outstanding Reviewer, European Computer Vision Association, 2024
  • Graduate School Presidential Science Scholarship, Korea Student Aid Foundation, 2024
  • 2nd Prize, BK21 Outstanding Paper Awards, POSTECH Graduate School of AI, 2024
  • 1st Prize, BK21 Outstanding Paper Awards, POSTECH Graduate School of AI, 2022
  • Qualcomm Innovation Fellowship Korea, Qualcomm, 2021
  • Silver Prize, 16th Samsung Electro-Mechanics Paper Awards, 2020
  • National Science and Engineering Scholarship, Korea Student Aid Foundation, 2013-2019

Academic Services

  • Conference Reviewer 2026: CVPR, NeurIPS
  • Conference Reviewer 2024: ECCV, SIGGRAPH Asia
  • Conference Reviewer 2023: ICML, ICCV, NeurIPS
  • Conference Reviewer 2022: ICLR, CVPR, ECCV, NeurIPS
  • Journal Reviewer: TPAMI, IJCV

Proficiencies

  • Korean (Native), English (Professional Working Proficiency)
  • PyTorch (Advanced), TensorFlow (Advanced)