Research at the intersection of machine learning, programming languages, and software
engineering has recently taken important steps in proposing learnable probabilistic models …

Measuring and evaluating source code similarity is a fundamental software engineering
activity that embraces a broad range of applications, including but not limited to code …

The current trend of scaling language models involves increasing both parameter count and
training dataset size. Extrapolating this trend suggests that training dataset size may soon be …

Sampling diverse programs from a code language model and reranking with model
likelihood is a popular method for code generation but it is prone to preferring degenerate …

Distribution shifts—where the training distribution differs from the test distribution—can
substantially degrade the accuracy of machine learning (ML) systems deployed in the wild …

Exploiting machine learning techniques for analyzing programs has attracted much
attention. One key problem is how to represent code fragments well for follow-up analysis …

Recent research has achieved impressive results on understanding and improving source
code by building up on machine-learning techniques developed for natural languages. A …

Pre-trained Generative Language models (eg, PLBART, CodeT5, SPT-Code) for source
code yielded strong results on several tasks in the past few years, including code generation …

We present a neural model for representing snippets of code as continuous distributed
vectors (``code embeddings''). The main idea is to represent a code snippet as a single fixed …

The ability to generate natural language sequences from source code snippets has a variety
of applications such as code summarization, documentation, and retrieval. Sequence-to …