Related papers: Context Composing for Full Line Code Completion

A transcompiler, also known as source-to-source translator, is a system that converts source code from a high-level programming language (such as C++ or Python) to another. Transcompilers are primarily used for interoperability, and to port…

Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development. As intelligent completion tools evolve, we need a robust evaluation…

Source code is rarely written in isolation. It depends significantly on the programmatic context, such as the class that the code would reside in. To study this phenomenon, we introduce the task of generating class member functions given…

Integrated Development Environments (IDEs) have become central to modern software development, especially with the integration of Artificial Intelligence (AI) to enhance programming efficiency and decision-making. The study of in-IDE…

Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model to understand the entire repository, reasoning over complex dependencies across functions,…

Understanding code is challenging, especially when working in new and complex development environments. Code comments and documentation can help, but are typically scarce or hard to navigate. Large language models (LLMs) are revolutionizing…

New information technologies provide a lot of prospects for performance improvement. One of them is "Dynamic Source Code Generation and Compilation". This article shows how this way provides high performance for engineering problems.

We advance the state-of-the-art in the accuracy of code prediction (next token prediction) used in autocomplete systems. First, we report that using the recently proposed Transformer architecture even out-of-the-box outperforms previous…

Code coverage is a widely used metric for quantifying the extent to which program elements, such as statements or branches, are executed during testing. Calculating code coverage is resource-intensive, requiring code building and execution…

Automatic code completion helps improve developers' productivity in their programming tasks. A program contains instructions expressed via code statements, which are considered as the basic units of program execution. In this paper, we…

Large Language Models (LLMs) have recently made significant advances in code generation through the 'Chain-of-Thought' prompting technique. This technique empowers the model to autonomously devise "solution plans" to tackle intricate…

Generative LLMs have been shown to effectively power AI-based code authoring tools that can suggest entire statements or blocks of code during code authoring. In this paper we present CodeCompose, an AI-assisted code authoring tool…

Program equivalence in linear contexts, where programs are used or executed exactly once, is an important issue in programming languages. However, existing techniques like those based on bisimulations and logical relations only target at…

Many of the existing approaches for program comprehension rely on the linguistic information found in source code, such as identifier names and comments. Semantic clustering is one such technique for modularization of the system that relies…

Code summaries help developers comprehend programs and reduce their time to infer the program functionalities during software maintenance. Recent efforts resort to deep learning techniques such as sequence-to-sequence models for generating…

Current search techniques are limited to standard RAG query-document applications. In this paper, we propose a novel technique to expand the code and index for predicting the required APIs, directly enabling high-quality, end-to-end code…

High-level synthesis, source-to-source compilers, and various Design Space Exploration techniques for pragma insertion have significantly improved the Quality of Results of generated designs. These tools offer benefits such as reduced…

Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive…

Effectively specifying and implementing robotic missions poses a set of challenges to software engineering for robotic systems. These challenges stem from the need to formalize and execute a robot's high-level tasks while considering…

Long-context modeling is one of the critical capabilities of language AI for digesting and reasoning over complex information pieces. In practice, long-context capabilities are typically built into a pre-trained language model~(LM) through…