Gender Male
I am an AI researcher at Harvard's School of Engineering and Applied Sciences, focusing on advancing trustworthy and equitable artificial intelligence. My research spans model fairness, uncertainty quantification methods, and scalable algorithms for reliable machine learning systems. Currently, I'm developing novel approaches for AI
safety and fairness, including robust reward modeling techniques and innovative metrics for measuring intersectional fairness across diverse demographic groups. My work has been published in leading machine learning and computer vision conferences, including NeurIPS, ICML, COLT, and ECCV.
