Osbert Bastani
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Decaf, a system that uses automatic feedback and search to significantly improve the semantic correctness and accuracy of neural decompilers, boosting the decompilation rate from 26.0% to 83.9% on ExeBench.
This paper provides a mathematical framework for studying different policy learning problems and shows reductions between them.
Papers
A Hierarchy of Policy Learning Problems
This paper provides a mathematical framework for studying different policy learning problems and shows reductions between them.