Language AI
LLM applications, conversational agents, retrieval-augmented generation, and text analytics.
Research
I care most about AI that works in practice. Every project I take on starts from a real problem, produces code and data, and is validated through publication or deployment. I involve graduate students as collaborators because the best ideas surface when experienced researchers and fresh perspectives collide. Much of this work feeds directly into course material and open-source tools.
Computer Vision
Object detection, image classification, medical imaging, and video understanding.
Multimodal Systems
Cross-modal reasoning, vision-language integration, and multi-source fusion.
Signal Processing
Time series analysis, anomaly detection, sensor fusion, and predictive modeling.
Applied Healthcare
Diagnostic questioning, medical image analysis, and clinical decision support.