William Jurayj

I am a PhD student at Johns Hopkins University, advised by Benjamin Van Durme, and an applied scientist intern at Amazon AGI working with Sapana Chaudhary. My research is centered on methods to help imperfect AI systems earn human trust. Recently, I’ve focused on making language models more effective at reasoning about and conveying their uncertainty, and at following complex rules and constraints faithfully.

Some questions that are currently on my mind:

• How do reasoning models’ uncertainties develop with increased inference budgets (Test-Time Scaling Confidence)? How can this behavior be learned (RLCM) or leveraged for early stopping (Conformal Thinking)?
• Can language models reason economically over large corpora of rules (Legal Logic Programs)? When are opinionated workflows more effective than general agents (Deontic Agentic Reasoning)?
• What learning algorithms will thrive in a data-scarce, compute-abundant regime?

Before I came to Hopkins, I worked at Abnormal Security as a machine learning engineer training behavioral models to detect compromised accounts. I completed my Bachelor’s and Master’s degrees at Brown, where I was fortunate to be advised by Carsten Eickhoff, Ellie Pavlick, and George Konidaris.