Dong-Kyum Kim

Postdoc @ Max Planck Institute for Security and Privacy (MPI-SP)

prof_pic.png

I am a postdoctoral researcher at the Max Planck Institute for Security and Privacy (MPI-SP). I completed my Ph.D. in Physics at KAIST, where I focused on AI applications in nonequilibrium physics. My research interests lie at the intersection of AI, complex systems, and nonequilibrium physics, with a particular focus on deep learning approaches.

I am passionate about using interdisciplinary approaches to gain a better understanding of how AI algorithms function and how we can improve their performance. To this end, I am currently exploring the use of neuroscience methods to gain insight into the behavior and performance of deep learning algorithms. I believe that this approach, known as brain-inspired AI, has the potential to lead to significant advances in the field of AI.

For more information, check out my publications and CV. I am always open to discussing my research and potential collaboration opportunities.

publications

2024

  1. Nat. Comm.
    Spontaneous emergence of rudimentary music detectors in deep neural networks
    Gwangsu Kim, Dong-Kyum Kim, and Hawoong Jeong
    Nature Communications 2024
  2. IJCV
    SUBTLE: An Unsupervised Platform with Temporal Link Embedding that Maps Animal Behavior
    Jea Kwon, Sunpil Kim, Dong-Kyum Kim, Jinhyeong Joo, SoHyung Kim, Meeyoung Cha, and C. Justin Lee
    International Journal of Computer Vision 2024

2023

  1. NeurIPS
    Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity
    Dong-Kyum Kim, Jea Kwon, Meeyoung Cha, and C. Justin Lee
    In Thirty-seventh Conference on Neural Information Processing Systems 2023
  2. PRR
    Multidimensional entropic bound: Estimator of entropy production for Langevin dynamics with an arbitrary time-dependent protocol
    Sangyun Lee, Dong-Kyum Kim, Jong-Min Park, Won Kyu Kim, Hyunggyu Park, and Jae Sung Lee
    Phys. Rev. Research Mar 2023
  3. BigComp
    Neural Classification of Terrestrial Biomes
    Vyacheslav Shen, Dong-Kyum Kim, Elke Zeller, and Meeyoung Cha
    In IEEE International Conference on Big Data and Smart Computing Mar 2023

2022

  1. NeurIPS-W
    Transformer needs NMDA receptor nonlinearity for long-term memory
    Dong-Kyum Kim, Jea Kwon, Meeyoung Cha, and C. Justin Lee
    In NeurIPS 2022 Memory in Artificial and Real Intelligence workshop Mar 2022
  2. PRR
    Estimating entropy production with odd-parity state variables via machine learning
    Dong-Kyum Kim, Sangyun Lee, and Hawoong Jeong
    Phys. Rev. Research Apr 2022
  3. PRR
    Inferring dissipation maps from videos using convolutional neural networks
    Youngkyoung Bae, Dong-Kyum Kim, and Hawoong Jeong
    Phys. Rev. Research Aug 2022

2021

  1. PRR
    Deep reinforcement learning for feedback control in a collective flashing ratchet
    Dong-Kyum Kim, and Hawoong Jeong
    Phys. Rev. Research Apr 2021

2020

  1. PRL
    Learning Entropy Production via Neural Networks
    Dong-Kyum Kim, Youngkyoung Bae, Sangyun Lee, and Hawoong Jeong
    Phys. Rev. Lett. Oct 2020
  2. JKPS
    Multi-label classification of historical documents by using hierarchical attention networks
    Dong-Kyum Kim, Byunghwee Lee, Daniel Kim, and Hawoong Jeong
    Journal of the Korean Physical Society Oct 2020