Search Results for author:
Found 7 papers, 2 papers with code
Multi-line AI-assisted Code Authoring
In this paper, we present how we scaled the product from displaying single-line suggestions to multi-line suggestions.
AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation
At the time of this writing, 16K developers have used it with 8% of their code coming directly from CodeCompose.
Learning to Learn to Predict Performance Regressions in Production at Meta
Catching and attributing code change-induced performance regressions in production is hard; predicting them beforehand, even harder.
Counterfactual Explanations for Models of Code
We integrate counterfactual explanation generation to models of source code in a real-world setting.
Improving Code Autocompletion with Transfer Learning
Software language models have achieved promising results predicting code completion usages, and several industry studies have described successful IDE integrations.
Programmatically Interpretable Reinforcement Learning
Unlike the popular Deep Reinforcement Learning (DRL) paradigm, which represents policies by neural networks, PIRL represents policies using a high-level, domain-specific programming language.
Neural Sketch Learning for Conditional Program Generation
We study the problem of generating source code in a strongly typed, Java-like programming language, given a label (for example a set of API calls or types) carrying a small amount of information about the code that is desired.
