Kuk Jin Jang

PRECISE University of Pennsylvania jangkj@seas.upenn.edu

prof_pic.jpg

Machine learning researcher specializing in trustworthy AI, multimodal learning, and uncertainty quantification for healthcare and robotics applications. Recently, I have focused on building trustworthy and reliable systems based on generative AI. With a Ph.D. in Electrical and Systems Engineering and over 30 publications, my work spans robust ECG classification, AI for ophthalmology and oculomics, and clinical interaction analysis.

I am committed to advancing AI in medicine and health, actively mentoring students, and contributing to the academic community and industry.

news

Dec 09, 2024 Our paper, “Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models,” has been accepted to AAAI 2025! :sparkles:
Nov 02, 2024 Our paper, “Fundus Image-based Visual Acuity Assessment with PAC-Guarantees,” has been accepted to ML4H :sparkles:
Oct 21, 2024 Our paper, “Credal Bayesian Deep Learning,” has been accepted for publication in the Transactions of Machine Learning Research
Jul 21, 2024 Paper accepted to APJO: “Development of Oculomics Artificial Intelligence for Cardiovascular Risk Factors: A Case Study in Fundus Oculomics for HbA1c Assessment and Clinically Relevant Considerations for Clinicians”

selected publications

  1. Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models
    Jean Park, Kuk Jin Jang, Basam Alasaly, and 5 more authors
    arXiv preprint arXiv:2408.12763, 2024
    arXiv
  2. DC4L: Distribution shift recovery via data-driven control for deep learning models
    Vivian Lin, Kuk Jin Jang, Souradeep Dutta, and 3 more authors
    In 6th Annual Learning for Dynamics & Control Conference, 2024
  3. Development of Oculomics Artificial Intelligence for Cardiovascular Risk Factors: A Case Study in Fundus Oculomics for HbA1c Assessment and Clinically Relevant Considerations for Clinicians
    Joshua Ong, Kuk Jin Jang, Seung Ju Baek, and 8 more authors
    Asia-Pacific Journal of Ophthalmology, 2024
  4. Credal Bayesian Deep Learning
    Michele Caprio, Souradeep Dutta, Kuk Jin Jang, and 4 more authors
    arXiv e-prints, 2024
    PDF
  5. Fundus Image-based Visual Acuity Assessment with PAC-Guarantees
    Sooyong Jang, Kuk Jin Jang, Hyonyoung Choi, and 4 more authors
    2024
    arXiv