Pythia: AI-assisted Code Completion System

2019-11-29 · Alexey Svyatkovskiy, Ying Zhao, Shengyu Fu, Neel Sundaresan

In this paper, we propose a novel end-to-end approach for AI-assisted code completion called Pythia. It generates ranked lists of method and API recommendations which can be used by software developers at edit time. The system is currently deployed as part of Intellicode extension in Visual Studio Code IDE. Pythia exploits state-of-the-art large-scale deep learning models trained on code contexts extracted from abstract syntax trees. It is designed to work at a high throughput predicting the best matching code completions on the order of 100 $ms$. We describe the architecture of the system, perform comparisons to frequency-based approach and invocation-based Markov Chain language model, and discuss challenges serving Pythia models on lightweight client devices. The offline evaluation results obtained on 2700 Python open source software GitHub repositories show a top-5 accuracy of 92\%, surpassing the baseline models by 20\% averaged over classes, for both intra and cross-project settings.

📄 PDF Abstract BibTeX arXiv:1912.00742

Code (1)

Microsoft/PTVS 공식 구현

Tasks

Code CompletionLanguage ModelingLanguage Modelling

You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion

2020-07-05 · Roei Schuster, Congzheng Song, Eran Tromer, Vitaly Shmatikov

Code autocompletion is an integral feature of modern code editors and IDEs. The latest generation of autocompleters uses neural language models, trained on public open-source code repositories, to suggest likely (not jus…

Code Completion Data Poisoning Model Poisoning

Pythia: A Customizable Hardware Prefetching Framework Using Online Reinforcement Learning

2021-09-24 · Rahul Bera, Konstantinos Kanellopoulos, Anant V. Nori, Taha Shahroodi 외

Past research has proposed numerous hardware prefetching techniques, most of which rely on exploiting one specific type of program context information (e.g., program counter, cacheline address) to predict future memory a…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds

2021-09-23 · Xuemeng Yang, Hao Zou, Xin Kong, Tianxin Huang 외

Outdoor scene completion is a challenging issue in 3D scene understanding, which plays an important role in intelligent robotics and autonomous driving. Due to the sparsity of LiDAR acquisition, it is far more complex fo…

3D Semantic Scene Completion 3D Semantic Segmentation Autonomous Driving Decoder+3

To Tab or Not to Tab: Measuring Critical Engagement in AI Code Completion Tools Using Behavioral Signals and Attention Checks

2026-06-29 · Jessica Hutchison, Ian Tyler Applebaum, Kenneth Angelikas, Kush Rakesh Patel 외 arxiv

AI code completion tools, such as Github Copilot, provide students with code suggestions to help them write programs. However, recent qualitative studies suggest that students fail to critically evaluate these suggestion…

Code Completion

Pythia: Grammar-Based Fuzzing of REST APIs with Coverage-guided Feedback and Learning-based Mutations

2020-05-23 · Vaggelis Atlidakis, Roxana Geambasu, Patrice Godefroid, Marina Polishchuk 외

This paper introduces Pythia, the first fuzzer that augments grammar-based fuzzing with coverage-guided feedback and a learning-based mutation strategy for stateful REST API fuzzing. Pythia uses a statistical model to le…

valid