Kimin Lee

I'm a Ph.D. student in School of Electrical Engineering at Korea Advanced Institute of Science and Technology (KAIST) where I'm advised by Prof. Jinwoo Shin and Prof. Song Chong. Prior to that, I received MS degree and BS degree in School of Electrical Engineering from KAIST.


  • Email
    • kiminlee at kaist dot ac dot kr // pokaxpoka at gmail dot com
  • Office
    • Room 917, N1 IT Building, KAIST, Daejeon
  • Phone: +82-42-350-7632

Research Interests

  • I'm interested in the fields of machine learning and deep learning. Here are my research topics and keywords:
    • Ensemble learning: multiple choice learning, independent ensemble.
    • Predictive uncertainty in machine/deep learning: detecting out-of-distribution, novelty detection.
    • Bayesian neural network: stochastic feedforward neural networks, variational inference, Monte Carlo estimation.


  • (2018/04)
    • Gave a talk on "Training Confidence-Calibrated Classifiers for Detecting Out-of-Distribution Samples” at NAVER AI.
  • (2018/02)
    • Our paper was accepted to CVPR 2018
      • Kibok Lee, Kimin Lee, Kyle Min, Yuting Zhang, Jinwoo Shin and Honglak Lee, "Hierarchical Novelty Detection for Visual Object Recognition".
  • (2018/01)
    • Our paper was accepted to ICLR 2018
      • K.Lee, H.Lee, K.Lee and J. Shin, "Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples".
  • (2018/01)
  • (2017/11)
  • (2017/11)
    • Gave a talk on "Confident Multiple Choice Learning” at SK Telecom
  • (2017/05)
    • Our paper was accepted to ICML 2017
      • K. Lee, C. Hwang, K. Park and J. Shin, "Confident Multiple Choice Learning".
  • (2016/03)
    • Our paper was accepted to SECON 2016
      • J. Jeong, K. Lee, B. Abdikamalov, K. Lee, and S. Chong, "TravelMiner: On the Benefit of Path-based Mobility Prediction".
  • (2015/12)
    • Our paper was accepted to INFOCOM 2016
      • K. Lee, Y. Kim, S. Kim, J. Shin, S. Shin and S. Chong, "Just-in-time WLANs: On-demand Interference-managed WLAN Infrastructures".