1 minute read

State of Deep Learning for Code Generation (DL4Code)

Machine learning models can now write decent code. Here are a list of key papers and models that address this task.
Code generation models generate code given some context that encodes user intent.

There have been a set of recent interesting results that apply large language models (e.g., GPT-3) to code generation (a.k.a program synthesis, program generation). The results so far have been competitive and some models have been integrated into developer productivity tools such as GitHub Copilot - an AI pair programming tool that supports programmers live as they write code (hint: it works quite well).

This post seeks to curate a running list of interesting papers, associated models and datasets that have been used to address this task.

Papers and Model Architectures

Several papers and models have been published.

Interested in more articles like this? Subscribe to get a monthly roundup of new posts and other interesting ideas at the intersection of Applied AI and HCI.

RELATED POSTS | research, stateof, machine learning

Read the Newsletter.

I write a monthly newsletter on Applied AI and HCI. Subscribe to get notified on new posts.

Feel free to reach out! Twitter, GitHub, LinkedIn