I am a research scientist in Meta's Applied AI organization, where I work on methods for improving and evaluating AI systems and agents through expert feedback, human-in-the-loop optimization, and data-efficient learning. Previously, I was on the Adaptive Experimentation team in Meta's Central Applied Science, where I developed Bayesian optimization and adaptive experimentation methods for turning human feedback, preferences, and behavioral signals into reliable learning signals for large-scale systems.

My research develops Bayesian and probabilistic methods for modeling and learning from human behavior, preferences, and feedback, with the goal of making adaptive learning systems more data-efficient, interpretable, and responsive to human context. I study how uncertainty, expert judgment, natural-language feedback, and behavioral signals can inform active data collection, preference learning, and optimization in both large-scale AI systems and small-sample decision settings. More broadly, I’m interested in how computational models can help us better understand human behavior and, in turn, design AI systems that learn from and interact with people in more reliable and meaningful ways. My work has been covered in the New York Times, LA Times, San Francisco Chronicle, the Verge, Washington Post, MIT Technology Review, Scientific American, and other places.

I received my Ph.D. in computer science from Stanford University advised by Sharad Goel and B.S. in computer science with a minor in probability and statistics from Georgia Institute of Technology. You can reach me at zylin@cs.stanford.edu.