Research

Reliable AI for uncertain, incomplete, real-world data

My research focuses on trustworthy and reliable artificial intelligence, with particular interests in multimodal machine learning, uncertainty quantification, fairness, generative AI, and AI for healthcare. I develop AI methods that can reliably learn and make decisions under uncertainty, incomplete information, and heterogeneous real-world data — applied to medical imaging, longitudinal health data, and Alzheimer's disease and related dementias (AD/ADRD).

01

Trustworthy & reliable AI

Fairness auditing and uncertainty quantification, so that models know when they don't know and treat patient groups equitably.

Representative work
Algorithmic Fairness of Machine Learning Models for Alzheimer's Disease Progression Prediction
JAMA Netw. Open 2023
Word-Sequence Entropy: Uncertainty Estimation in Free-Form Medical Question Answering
EAAI 2025
Fairness Verification of AI Algorithms in Predicting Progression of Alzheimer's Disease
Preprint
02

Multimodal & generative AI

Learning from images, text, and structured data together, and generative models that create useful, diverse, and evaluable outputs.

Representative work
DCG-GAN: Design Concept Generation with Generative Adversarial Networks
Design Science 2024
DDE-GAN: Integrating a Data-Driven Design Evaluator into GANs for Desirable and Diverse Concept Generation
J. Mech. Design 2023
Leveraging End-User Data for Enhanced Design Concept Evaluation: A Multimodal Deep Regression Model
J. Mech. Design 2021
03

AI for healthcare

Medical imaging, longitudinal health data, and Alzheimer's disease and related dementias (AD/ADRD).

Representative work
ReMiND: Recovery of Missing Neuroimaging using Diffusion Models with Application to Alzheimer's Disease
Imaging Neurosci. 2024
Interpretable Medical Deep Framework by Logits-constraint Attention Guiding Graph-based Multi-scale Fusion for Alzheimer's Disease Analysis
Pattern Recogn. 2024
See all publications →