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

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 …

Writing tests is a time-consuming yet essential task during software development. We
propose to leverage recent advances in deep learning for text and code generation to assist …

Source code summaries are important for program comprehension and maintenance.
However, there are plenty of programs with missing, outdated, or mismatched summaries …

Developers deal with code-change-related tasks daily, eg, reviewing code. Pre-trained code
and code-change-oriented models have been adapted to help developers with such tasks …

Context: Large language models trained on source code can support a variety of software
development tasks, such as code recommendation and program repair. Large amounts of …

Pretrained language models have been shown to be effective in many software-related
generation tasks; however, they are not well-suited for editing tasks as they are not designed …

Representing code changes as numeric feature vectors, ie, code change representations, is
usually an essential step to automate many software engineering tasks related to code …

Software comments sometimes are not promptly updated in sync when the associated code
is changed. The inconsistency between code and comments may mislead the developers …

The increasing use of Large Language Models (LLMs) in software development has
garnered significant attention from researchers assessing the quality of the code they …