Learning, Discovery, Reasoning (LDR) Group

The JHU LDR group conducts interdisciplinary research in AI, with a focus on Machine Learning, Computer Vision, and Healthcare & Biomedical Applications. Our research is inspired by the charms and curses from the diverse and imperfect real-world data, which spans various forms (e.g., images, videos, text, voice, signals) and scales (e.g., molecules, cells, organs, individuals, populations). However, data alone is just a static archive, its true power emerges only when properly interpreted, analyzed, and applied. We develop data-driven methods that transform data into actionable intelligence, covering the full spectrum from learning patterns in complex data, to discovering novel and meaningful insights, and ultimately reasoning for informed decision-making.

With the ultimate goal of advancing healthcare outcomes, we care about: (1) Developing foundational theories in machine learning, and practical algorithms for healthcare & biomedical applications, and (2) Translating our scientific discoveries from the bench to real-world impact at the bedside.

Our work covers a wide range of disciplines. Naturally, we publish in top venues ranging from computer vision (e.g., CVPR, ICCV, ECCV) and machine learning (e.g., NeurIPS, ICLR, ICML) conferences, to medical conferences and journals (e.g., MICCAI, IPMI, IEEE TMI).

Team

Principal Investigator

  • Peirong Liu

PhD

  • Jun Wang (PhD Student in ECE, 2025 - Present): Generative Models; Anomaly Detection

Master

  • Karol Sun (Master's Student in BME, 2025 - Present): Foundation Models, Image Registration

Research Topics

Here are some topics that I am particularly interested in. Based on your interests, we will work together to design your research project after you join our group.
  • Machine Learning & Computer Vision:
    • Generative Models; Representation Learning
    • Anomaly Detection; Uncertainty Estimation
    • Physics-informed Deep Learning; Spatiotemporal Modeling
  • Medical Image Analysis:
    • Multi-modal Foundation Models in Medical Imaging
    • Image Generation, Reconstruction, Segmentation, Registration
    • Lesion Detection, Segmentation and Growth Modeling
  • Clinical Applications:
    • Brain Imaging; Diffusion MRI; Functional MRI; Cortical Surface
    • Disease Diagnosis; Interventional Treatment Planning and Risk Evaluation

Openings

I am looking for self-motivated students with solid mathematical background and strong coding skills in machine learning and computer vision. Research experience in healthcare and biomedical applications is a plus, but not required.

Application Email: peirong[at]jhu.edu (Please be advised that the best way to get in touch with me is by emailing me directly — I will review all submissions and reach out to candidates whom I believe are a good fit.)

-> Prospective PhD: If you are interested in a fully-funded PhD position starting in Fall 2026, please email me your CV, transcripts, as well as a brief summary on your background and research interests (Subject: "Prospective PhD 2026").

-> Current JHU MS / Undergrad: If you are at JHU and are looking for potential advisors, please email me directly (Subject: "JHU Student").

-> Prospective Postdoc: If interested, please email me your CV and a research statement (maximum 4 pages) (Subject: "Prospective Postdoc").

-> Prospective Intern: Self-motivated interns are always welcome to join our group. If interested, please email me your CV and a brief summary on your research interests (Subject: "Prospective Intern").