We propose Corder, a self-supervised contrastive learning framework for source code
model. Corder is designed to alleviate the need of labeled data for code retrieval and code …

Exploit code is widely used for detecting vulnerabilities and implementing defensive
measures. However, automatic generation of exploit code for security assessment is a …

Recent work learns contextual representations of source code by reconstructing tokens from
their context. For downstream semantic understanding tasks like summarizing code in …

The Software Naturalness hypothesis argues that programming languages can be
understood through the same techniques used in natural language processing. We explore …

Code smells are structures in code that often harm its quality. Manually detecting code
smells is challenging, so researchers proposed many automatic detectors. Traditional code …

As artificial intelligence advances, source code completion assistants are becoming more
advanced and powerful. Existing traditional assistants are no longer up to all the developers' …

The Transformer architecture and transfer learning have marked a quantum leap in natural
language processing, improving the state of the art across a range of text-based tasks. This …

One of the most common solutions adopted by software researchers to address code
generation is by training Large Language Models (LLMs) on massive amounts of source …

Neural Language Models of Code, or Neural Code Models (NCMs), are rapidly progressing
from research prototypes to commercial developer tools. As such, understanding the …

Code smells are poorly designed code structures indicating that the code may need to be
refactored. Recognizing code smells in practice is complex, and researchers strive to …