Hello! I'm Andrew Chung, a MSCS Student at Columbia with a keen interest in AI Safety, ML Interpretability, and Applied AI. I previously attended Emory University for my Bachelors, graduating with Highest Honors in Computer Science with an AI focus. Currently, I am pursuing research at Rutgers in interpretable AI.
I envision AI systems to be highly personalized and adaptive in the future. To attain this vision I am currently interested in how we can better evaluate, interpret, and control AI models and LLMs for safe, intelligent usage.
Outside the lab or the classroom, you'll find me exploring photography, music, or rating restaurants on Beli. I'm always eager to learn, build, and share what I discover along the way.