Dongmin Kim

Dongmin Kim

AI Researcher @KAIST

About Me

Nice to meet you! I’m Dongmin Kim from Korea. I’m deeply interested in SW & Mathematical background behind it, and now trying to change the way people live with SW technology. I’m using this blog as my storage for my knowledges and technologies that I’ve been now working for. For more formal introduction of me, you may visit my CV here.

Publications

  • WaveBound: Dynamically Bounding Error for Stable Time-Series Forecasting

    • Youngin Cho,* Daejin Kim,* Dongmin Kim, Mohammad Azam Khan, and Jaegul Choo (: equal contributions) Conference on Neural Information Processing Systems (NeurIPS), 2022, *Accepted (25.6% acceptance rate).

  • Residual Correction in Real-Time Traffic Forecasting

    • Daejin Kim,* Youngin Cho,* Dongmin Kim, Cheonbok Park, and Jaegul Choo (: equal contributions) ACM International Conference on Information and Knowledge Management (CIKM), 2022, *Accepted.

  • Deep Imbalanced Time-series Forecasting via Local Discrepancy Density

    • Junwoo Park, Jungsoo Lee, Youngin Cho, Woncheol Shin, Dongmin Kim, Jaegul Choo, and Edward Choi

      European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), 2023

Academics

  • [Aug 2021 - Present] Master Student at KAIST GSAI, South Korea (Advisor: Prof. Jaegul Choo)
  • [Mar 2014 - Feb 2021] Bachelor’s Degree in Global Economics and Computer Science at Sungkyunkwan University, South Korea
  • [Aug 2019 - Nov 2019] Exchange Student at The Chinese University of Hong Kong
  • [Mar 2011 - Feb 2014] Chinese Department at Myungduk Foreign Language High School, South Korea

Professional Experiences

  • [Jun 2021 - Aug 2021] Intern, KT Corp., South Korea | SW Developer
  • [Jan 2020 - Feb 2020] Intern, Samil PwC, South Korea | Developed RPA Service using UiPath and Python

Projects

Here are some lists of projects that I’ve worked. Visit here for details.

  • ROK ADD PIBOT Project
  • KT Genio Topological Visualization
  • Crude Oil Price Prediction based on GKFN
  • Tensor Decomposition for Deepfake Detection
  • Pet-caring Robots
  • GLIF Website Project

Programming Practice

I believe programming practice is essential to SW development, so I sometimes use those platforms below for implementation skills.

  1. Codeforces for my competitive programming experience, and recently joined codeforces round #722 (May 25th, 2021), and have participated 1 competition(s) in total. My handle is carrtesy.
  2. Baekjoon is a Korean online judge platform for Programming Practice, and I’ve solved 200 problems and ranked 8072 until May 19th, 2021. Here is my info.
  3. Programmers is another Korean Programming Practice platform, and I’ve solved 131 programming & SQL problems and ranked 2353 until May 19th, 2021.

Schedules

To make an appointment, see my schedules below.