Scholar
William Jurayj
Google Scholar ID: y4Ez98cAAAAJ
Johns Hopkins University
Citations & Impact
Citations
34
H-index
5
i10-index
0
Publications
6
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Publications: [Test-Time Scaling Confidence], [Legal Logic Programs], [Programming MDP Components].
Research Experience
- Worked as a machine learning engineer at Abnormal Security, training models to detect compromised accounts.
Education
- PhD student at Johns Hopkins University, advised by Benjamin Van Durme; Bachelor’s and Master’s degrees from Brown University, advised by Carsten Eickhoff, Ellie Pavlick, and George Konidaris.
Background
- Research interests: methods to help imperfect AI systems earn human trust, particularly in making language models more effective at reasoning about and conveying their uncertainty; interested in the interpretability offered by symbolic reasoning systems and in techniques for adaptation to low-resource, high-stakes domains.
Miscellany
- Contact: w [my last name] 1 at jhu dot edu
