Automatic program understanding and generation techniques could significantly advance
the productivity of programmers and have been widely studied by academia and industry …

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

Modern language models (LMs) have been successfully employed in source code
generation and understanding, leading to a significant increase in research focused on …

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

Code prediction, more specifically autocomplete, has become an essential feature in
modern IDEs. Autocomplete is more effective when the desired next token is at (or close to) …

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been
widely adopted on downstream tasks for source code understanding. However, compared to …

Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned
widespread attention from both academia and industry. Attributed to the superior ability in …

Neural models of code have shown impressive results when performing tasks such as
predicting method names and identifying certain kinds of bugs. We show that these models …

Searching and reusing code snippets from open-source software repositories based on
natural-language queries can greatly improve programming productivity. Recently, deep …

Code completion, a highly valuable topic in the software development domain, has been
increasingly promoted for use by recent advances in large language models (LLMs). To …