Chirag Agarwal

Chirag Agarwal is an Assistant Professor of Data Science at the University of Virginia School of Data Science, where he leads the Aikyam Lab focused on trustworthy machine learning. He holds a Ph.D. in Electrical and Computer Engineering from the University of Illinois at Chicago.

His research develops frameworks for explainable, fair, and robust AI systems, supported by grants from Adobe, Microsoft, and Google. Core research themes include:

• Explainability methods for complex models
• Bias mitigation in vision-language systems
• Privacy-preserving machine learning
• Safety certification for large language models

Publications demonstrate cross-cutting work in ML theory and applications, with recent emphasis on medical AI safety, multilingual reasoning, and adversarial robustness.