An increasingly popular set of techniques adopted by software engineering (SE)
researchers to automate development tasks are those rooted in the concept of Deep …

This paper explores the limits of the current generation of large language models for
program synthesis in general purpose programming languages. We evaluate a collection of …

The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

Automated Program Repair (APR) helps improve the efficiency of software development and
maintenance. Recent APR techniques use deep learning, particularly the encoder-decoder …

A transcompiler, also known as source-to-source translator, is a system that converts source
code from a high-level programming language (such as C++ or Python) to another …

Code intelligence leverages machine learning techniques to extract knowledge from
extensive code corpora, with the aim of developing intelligent tools to improve the quality …

The problem of fixing errors in programs has attracted substantial interest over the years.
The key challenge for building an effective code fixing tool is to capture a wide range of …

Abstract Machine learning-based program analyses have recently shown the promise of
integrating formal and probabilistic reasoning towards aiding software development …

We consider the problem of learning to repair programs from diagnostic feedback (eg,
compiler error messages). Program repair is challenging for two reasons: First, it requires …

In this paper, we address the problem of automatic repair of software vulnerabilities with
deep learning. The major problem with data-driven vulnerability repair is that the few …