profile picture

Yucheol Cho

AI Researcher

Education

Ph.D., Electrical Engineering

KAIST, Daejeon
03/21 - 02/25

M.S., Electrical Engineering

KAIST, Daejeon
03/18 - 02/20

B.S., Electronic & Electrical Engineering

Hongik University, Seoul
03/11 - 02/18

Languages

  • Korean (Native)
  • English (Professional)

Interests

  • Vision-language model
  • Knowledge distillation
  • Time series anomaly detection
  • Deep learning for physics

About Theme

Career Profile

Yucheol Cho received his Ph.D. from the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea, in 2025, under the supervision of Professor Dae-Shik Kim .

He earned his master’s degree in 2020 from KAIST, specializing in first-principles-based semiconductor device simulations. Afterward, he worked at Samsung Electronics for a year until 2021. During his time at Samsung, he developed a strong interest in deep learning, which led him to pursue a Ph.D. in the field of deep learning and machine learning, aiming to become an expert in AI.

His doctoral research included topics related to data engineering, focusing on data generation, training, and inference. He has a broad interest in various AI-related fields, including multimodal models, knowledge distillation, time series anomaly detection, and deep learning for physics. After completing his Ph.D., he worked at the Agency for Defense Development (ADD), contributing to AI research for national defense applications.

He is currently serving as an Assistant Professor in the Department of Electronic Engineering at Hanbat National University.

Experiences

Hanbat National University

09/25 - present
Assistant Professor

Department of Electronic Engineering

Agency for Defense Development (ADD)

04/25 - 08/25
Senior Researcher

Defense AI technology development

Samsung Electronics (DIT center)

03/20 - 02/21
Research Engineer

Machine learning based device simulations

Samsung Electronics (Semiconductor research center)

01/19 - 02/19
Internship Course

Device simulations

Electronics and Telecommunications Research Institute (ETRI)

06/17 - 08/17
Internship Course

Device experiments

Awards

The 5th Korea Artificial Intelligence Conference (10/24) - Outstanding Paper Award
Smart HACCP Data Challenge (11/23) - Top Prize
Samsung Outstanding Internship Prize (02/19) - Samsung Semiconductor Research Center
KT Group Scholarship Student (01/17 - 12/17) - KT IT MASTER

Publications

Journal

  • Generality-aware Self-supervised Transformer for Multivariate Time Series Anomaly Detection
    • Yucheol Cho, Jae-Hyeok Lee, Gyeongdo Ham, Donggon Jang, and Dae-shik Kim
    Applied Intelligence, 55.7, 604, Mar. 2025.
  • Difficulty Level-based Knowledge Distillation
    • Gyeongdo Ham*, Yucheol Cho*, Jae-Hyeok Lee, Minchan Kang, Gyuwon Choi, and Daeshik Kim (*Equal contribution)
    Neurocomputing, 606, 128375, Nov. 2024.
  • SemiH: DFT Hamiltonian Neural Network Training with Semi-supervised Learning
    • Yucheol Cho*, Guenseok Choi*, Gyeongdo Ham, Mincheol Shin† and Daeshik Kim† (*Equal contribution, †Equal correspondence)
    Machine Learning: Science and Technology, 5(3), 035060, Sep. 2024.
  • Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning
    • Seonghak Kim*, Gyeongdo Ham*, Yucheol Cho*, and Daeshik Kim (*Equal contribution)
    IEEE Transactions on Knowledge and Data Engineering, Aug. 2024.
  • Ambiguity-aware Robust Teacher (ART): Enhanced Self-knowledge Distillation Framework with Pruned Teacher Network
    • Yucheol Cho*, Gyeongdo Ham*, Jae-Hyeok Lee, and Daeshik Kim (*Equal contribution)
    Pattern Recognition, Vol. 140C, 109541, Aug. 2023.
  • P-PseudoLabel: Enhanced Pseudo-Labeling Framework with Network Pruning in Semi-Supervised Learning
    • Gyeongdo Ham*, Yucheol Cho*, Jae-Hyeok Lee, and Daeshik Kim (*Equal contribution)
    IEEE Access, Vol. 10, 115652 - 115662, Oct. 2022.
  • Principles-based Quantum Transport Simulations of Interfacial Point Defect Effects on InAs Nanowire Tunnel Field- Effect Transistors
    • Hyeongu Lee, Yucheol Cho, Seonghyeok Jeon, and Mincheol Shin
    IEEE Transctions on Electron Devices, vol. 68, pp. 5901 - 5907, Nov. 2021.

    Conference

  • MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation
    • Donggon Jang*, Yucheol Cho*, Suin Lee, Taehyeon Kim, and Daehsik Kim (*Equal contribution)
    International Conference on Learning Representations (ICLR), Singapore, Apr 24-28, 2025.
  • DFT Hamiltonian Neural Network Training with Semi-supervised Learning
    • Yucheol Cho*, Guenseok Choi*, Gyeongdo Ham, Mincheol Shin† and Daehsik Kim† (*Equal contribution, †Equal correspondence)
    NeurIPS workshop on Machine Learning and the Physical Sciences (ML4PS), New Orleans, Dec 15-16, 2023.
  • First-principles Study on As Antisites in InGaAs Alloys, GaAs and InAs
    • Yucheol Cho, Gyeongdo Ham and Daehsik Kim
    International Workshop on Computational Nanotechnology (IWCN), Barcelona (Spain), June 12-16, 2023.
  • Effect of Trap on Carrier Transport in InAs FET with Al2O3 Oxide
    • Mincheol Shin, Yucheol Cho, and Seong Hyeok Jeon
    International Conference on Simulation of Semiconductor Processes and Devices (SISPAD), IEEE, Udine, Italy, 2019.
  • Atomistic Simulation of GaSb/InAs Ultra-thin-body Tunnel FETs
    • Yucheol Cho, and Mincheol Shin
    Nano Korea, Kintex, Ilsan, Korea, 2019.
  • GaSb/InAs Heterojunction-based Tunnel FETs: A first-principles study
    • Yucheol Cho, Yunhee Chang, Mincheol Shin
    The 26th Korean Conference on Semiconductors, Jeongseon, 2019.

    Skills & Proficiency

    Python

    Pytorch

    Matlab

    C/C++

    SIESTA, OpenMX, VASP