Kanghyun Choi

I am a graduate student in the Department of Computer Science at Seoul National University. My research interests are mainly focusing on building efficient neural network architecture by neural architecture search (NAS) or neural network quantization.

Publication


    • It’s All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher
      • Kanghyun Choi, Hyeyoon Lee, Deokki Hong, Joonsang Yu, Noseong Park, Youngsok Kim, Jinho Lee
        CVPR, 2022, Selected for an oral presentation

    • Enabling Hard Constraints in Differentiable Neural Network and Accelerator Co-Exploration
      • Deokki Hong, Kanghyun Choi, Hyeyoon Lee, Joonsang Yu, Noseong Park, Youngsok Kim, Jinho Lee
        DAC, 2022

    • Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples
      • Kanghyun Choi, Deokki Hong, Noseong Park, Youngsok Kim, Jinho Lee
        NeurIPS, 2021, Github, arXiv, Slides

    • DANCE: Differentiable Accelerator/Network Co-Exploration
      • Kanghyun Choi1, Deokki Hong1, Hojae Yoon1, Joonsang Yu, Youngsok Kim, Jinho Lee
        DAC, 2021, arXiv, Slides

1 indicates co-first authors

Teaching Experience


    • Multi-core and GPU Programming (CSI4119)
      • Teaching Assistant, Spring 2021,2022
    • Logic Circuit Design (CSI2111)
      • Teaching Assistant, Fall 2020
  • Email: kanghyun.choi@yonsei.ac.kr
  • Github: github.com/iamkanghyunchoi
  • CV : CV