paper-conference

Coeditor, a code editing model trained on code commits, surpasses previous code completion methods and unveils a new multi-round auto-editing application.

Combining the strengths of CodeT5 and static analysis to predict Python type annotations.

A Monte Carlo expectation-maximization algorithm for learning stochastic kinodynamic models from noisy and indirect observations.

A controller synthesis framework that automatically handles delay compensation for distributed robotic systems using receding horizon control.

A neural architecture for type inference that combines the strength of explicit program analysis with graph neural networks.

A new blackbox complexity testing technique for determining the worst-case asymptotic complexity using program synthesis.