About Me

Kang Jinho

I obtained both my Bachelor's and Master's degrees from the Department of Computer Science and the Department of Artificial Intelligence at the University of Seoul. During my Master's program, I had the privilege of being jointly supervised by Prof. Kyungwoo Song at Yonsei University and Prof. Jiyeong Jung at the University of Seoul. Starting in Fall 2026, I will be pursuing my PhD in Computer Science at the University of Texas at Dallas.

My research has focused on improving the interpretability and reliability of Artificial Intelligence through AI robustness, causal inference, and domain generalization and adaptation.

My Career

Data Science Researcher @ Yonsei University

Institute of Data Science, Yonsei University (Inter-collegiate Research Institute)

August 2025 – Present
Yonsei University, Seoul, South Korea

Obtained M.S. @ University of Seoul

Department of Artificial Intelligence

March 2023 – August 2025
University of Seoul, Seoul, South Korea

Visiting Researcher @ Carnegie Mellon University

Supported by IITP (Institute for Information & Communication Technology Planning & Evaluation)

September 2024 – February 2025
Carnegie Mellon University, Pittsburgh, Pennsylvania, United States

Graduate Researcher @ University of Seoul

Machine Learning and Artificial Intelligence Lab

April 2023 – August 2025
University of Seoul, Seoul, South Korea

Obtained B.S. @ University of Seoul

Department of Computer Science and Engineering

March 2016 – April 2023
University of Seoul, Seoul, South Korea

Undergraduate Researcher @ University of Seoul

Machine Learning and Artificial Intelligence Lab

September 2021 – April 2023
University of Seoul, Seoul, South Korea

My Publications

Google Scholar

Peer Reviewed

  • Bibimbap: Ensembling Diverse Pretrained Models for Domain Generalization in Domain Shifted Task

    Jinho Kang, Taero Kim, Yewon Kim, Changdae Oh, Jiyoung Jung, Rakwoo Chang, and Kyungwoo Song
    Pattern Recognition 2024. (SCIE, JCR 2022 IF=8.0)

  • Sequential Treatment Effect Estimation with Variational Transformers: Application to COVID-19 Infection Clusters

    Jinho Kang, Sungjun Lim, Hojun Park, Jaehun Jung, Jiyoung Jung, and Kyungwoo Song
    IJCAI 2024 Workshop (AI for Time Series Analysis), The Best Paper Honorable Mention Award

  • Few-Shot PPG Signal Generation via Guided Diffusion Models

    Jinho Kang, Yongtaek Lim, KyuHyung Kim, Hyeonjeong Lee, KwangYong Kim, Minseong Kim, Jiyoung Jung, and Kyungwoo Song
    IEEE Sensors Journal 2024. (SCIE, JCR 2022 IF=4.3)

  • Flat Posterior Does Matter For Bayesian Model Ensemble

    Sungjun Lim, Sooyon Kim, Jeyoon Yeom, Hoyoon Byun, Jinho Kang, and Kyungwoo Song
    UAI 2025 (AI Top-tier Conference).

  • Multi-Query Frequency Prompting for Biosignal Domain Adaptation

    Jinho Kang*, Hoyoon Byun*, Taero Kim, Yewon Kim, Jiyoung Jung, and Kyungwoo Song
    Knowledge-Based System 2025. (SCIE, JCR 2024 IF=7.6)

  • Causal Effect Variational Transformer for Public Health Measures and COVID-19 Infection Cluster Analysis

    Jinho Kang, Sungjun Lim, Hojun Park, Jaehun Jung, Jiyoung Jung, and KyungWoo Song
    CIKM 2025 (AI/Data Mining Top-tier Conference).

  • Enhancing Global and Local Context Modeling in Time Series Through Multi-Step Transformer-Diffusion Interaction

    Dagyeong Na, Jinho Kang, Byoungwoo Kang, Junseok Kwon
    IEEE Access 2025. (SCIE, JCR 2024 IF=3.9)

  • Towards Generalizable Time Series Forecasting via IB-Regularized Transformer-Diffusion

    Dagyeong Na, Jinho Kang, Junseok Kwon
    ICDM 2025 short paper (AI/Data Mining Top-tier Conference).

Under Review

  • CBPE: Causal relation-aware Blood Pressure Estimation with Multimodal Data

    Hoyoon Byun, Sumin Park, Jinho Kang, Hyeonjeong Lee, Minseong Kim, Doosik Kim, Kwangyong Kim and Kyungwoo Song
    (Submitted to AI Conference 2025.)

© Machine Learning and Artificial Intelligence Lab @ Yonsei University

(* equal contribution)

My Projects

GitHub

Multi Query Frequency Prompting for Domain Adaptation

Novel prompt-learning framework that enhances deep learning models for blood pressure prediction from PPG signals by improving robustness and adaptation to diverse datasets and conditions.

Sequential Cluster Regression for COVID Epidemiology

Developed a machine learning model using a Transformer to predict the infection spread and duration of coronavirus clusters by embedding and processing both cluster and patient information.

Data Augmentation of PPG Signals Through Guided Diffusion

Address data imbalance in medical datasets by using regressor-guided diffusion models to generate high-quality, diverse PPG signals, significantly enhancing Arterial Blood Pressure predictions.

Causal Discovery in Photoplethysmography Attributes

Uncovering causal relationships among PPG signals and diverse physiological attributes (e.g., race, age) to enable robust and accurate arterial blood pressure (ABP) estimation.

Failure-Aware Causal Modeling through FMEA-Driven LLM Adaptation

Leveraging domain-specific technical documents from the automotive industry to pretrain and adapt LLMs for generating accurate, component-targeted FMEA scenarios via causal reasoning.


Awards

  • The Best Paper Honorable Mention Award

    International Joint Conference on Artificial Intelligence (IJCAI) 2024, August
    An award for "Sequential Treatment Effect Estimation with Variational Transformers" from IJCAI 2024 workshop AI4TS

  • Summer Academic Paper Presentation Conference

    Korean Data Analysis Society (KDAS) 2023, July
    An award for 'Bibimbap : Pre-trained models ensemble for Domain Generalization'

© Machine Learning and Artificial Intelligence Lab @ Yonsei University