CV

PhD student at Seoul National University focusing on deep learning and time series analysis, with growing interest in time series foundation models, time-series–language models, and Physical AI.

• 2023 - present

  Seoul, South Korea

  PhD

  Seoul National University

  Industrial Engineering

  • Advisor: Prof. Jaewook Lee
  • Research: deep learning, time series analysis

• 2017 - 2023

  Seoul, South Korea

  BS

  Seoul National University

  Industrial Engineering

• Kim, Dongbin, Park, Jinseong, Lee, Jaewook, & Kim, Hoki (2024). Are self-attentions effective for time series forecasting? Advances in Neural Information Processing Systems, 37, 114180–114209.
• Kim, Dongbin, Park, Youngjoo, Jeong, Woojin, & Lee, Jaewook (2026). Local geometry attention for time series forecasting under realistic corruptions. In Proceedings of the 14th International Conference on Learning Representations.
• Kim, Dongbin, Lee, Jaewook, & Kim, Hoki (2026). Pattern-guided forecasting framework for metal price prediction with grouping decomposed series. Financial Innovation, 12(1), 45.
• Choi, Yujin, Kim, Dongbin, & Lee, Jaewook (2025). Temporal consistency ensemble empirical mode decomposition for forecasting practical metal price. Engineering Applications of Artificial Intelligence, 158, 111490.

• Kim, Dongbin, Shin, Geonwoo, Choi, Yujin, Park, Soyeon, & Lee, Jaewook (2026). A locally tokenized generative model for robust time-series watermarking. Manuscript submitted to NeurIPS 2026.
• Kim, Dongbin, Lee, Seungyun, Shin, Geonwoo, & Lee, Jaewook (2026). Discretizing continuous time series for imputation with masked diffusion training. Manuscript submitted to NeurIPS 2026.
• Kim, Dongbin, Jeong, Woojin, & Lee, Jaewook (2026). Learning from dynamics: Schedule-free neural Lyapunov control. Manuscript submitted to NeurIPS 2026.

• 2025

  Method and Apparatus for Training Artificial Intelligence Model for Time Series Forecasting, Method and Apparatus for Time Series Forecasting Using the Same

  Korean Intellectual Property Office (KIPO)

  Application No. 10-2025-0143602 (filed)

• 2026

  System and Method for Robust Time Series Forecasting Based on Local Geometry Attention

  Korean Intellectual Property Office (KIPO)

  Application filed (no. pending)

• Local Geometry-Based Attention Mechanisms for Time Series Transformers

  Principal Investigator, Doctoral Student Research Grant, National Research Foundation of Korea (NRF)

• Initial Input Quantity Recommendation System

  COSMAX — Project lead, model development and analysis

• Fall 2025

  Seoul, South Korea

  Lecturer

  • Sungkyunkwan University
  • Consumer Big Data Analysis (CON3032, 3 credits)

• 2023 – 2026

  Seoul, South Korea

  Teaching Assistant

  • Advanced Expert Program in Big Data, AI & FinTech, Seoul National University
  • Machine Learning & Deep Learning (six semesters)

• 2023 – 2025

  Seoul, South Korea

  Teaching Assistant

  • HD Hyundai–SNU AI Advanced Program
  • Nonlinear Time Series Analysis (three semesters)

• 2023 – 2025

  Seoul, South Korea

  Teaching Assistant

  • Samsung Electronics Data Science Education
  • Linear Algebra & Optimization (four sessions)

• 2024

  Seoul, South Korea

  Teaching Assistant

  • Korea Banking Institute Data Science Capability Enhancement Program
  • Mathematics and Statistical Analysis for Data Science (one session)

• 2021–2022

  Merit-Based Scholarship (Undergraduate)

  Seoul National University

  Awarded for three semesters: Spring 2021, Fall 2021, Fall 2022.

• 2023–2024

  Merit-Based Scholarship (Graduate, Integrated MS-PhD)

  Seoul National University

  Awarded for three semesters: Fall 2023, Spring 2024, Fall 2024.