Related papers: KOALA: a Configurable Tool for Collecting IDE Data…
Large code models (LCMs) have remarkably advanced the field of code generation. Despite their impressive capabilities, they still face practical deployment issues, such as high inference costs, limited accessibility of proprietary LCMs, and…
We introduce control models for LLM-powered code completion in JetBrains IDEs: ML classifiers which trigger inference and filter the generated suggestions to better align them with users and reduce unnecessary requests. To this end, we…
Programming projects are essential in computer science education for bridging theory with practice and introducing students to tools like Git, IDEs, and debuggers. However, designing and evaluating these projects (especially in MOOCs)can be…
The integration of Artificial Intelligence (AI) in education requires scalable and efficient frameworks that balance performance, adaptability, and cost. This paper addresses these needs by proposing a shared backbone model architecture…
Instruction tuning improves the performance of large language models (LLMs), but it heavily relies on high-quality training data. Recently, LLMs have been used to synthesize instruction data using seed question-answer (QA) pairs. However,…
AI Code Completion (e.g., GitHub's Copilot) has revolutionized how computer science students interact with programming languages. However, AI code completion has been studied from the developers' perspectives, not the students' perspectives…
Automatic analysis of teacher and student interactions could be very important to improve the quality of teaching and student engagement. However, despite some recent progress in utilizing multimodal data for teaching and learning…
Applications in the smart industry domain, such as interaction with collaborative robots using vocal commands or machine vision systems often requires the deployment of deep learning algorithms on heterogeneous low power computing…
In software engineering, a great number of new approaches are being actively researched, and a lot of tools are being developed based on them. These tools require a framework for their creation and an opportunity to be used by potential…
Data profiling is critical in machine learning for generating descriptive statistics, supporting both deeper understanding and downstream tasks like data valuation and curation. This work addresses profiling specifically in the context of…
Evaluating in-the-wild coding capabilities of large language models (LLMs) is a challenging endeavor with no clear solution. We introduce Copilot Arena, a platform to collect user preferences for code generation through native integration…
The increasing demand for programmers has led to a surge in participants in programming courses, making it increasingly challenging for instructors to assess student code manually. As a result, automated programming assessment systems…
The automatic collection of stack traces in bug tracking systems is an integral part of many software projects and their maintenance. However, such reports often contain a lot of duplicates, and the problem of de-duplicating them into…
Instruction-tuned large language models have demonstrated remarkable capabilities in following human instructions across various domains. However, their proficiency remains notably deficient in many low-resource languages. To address this…
This paper proposes an open source visual analytics tool consisting of several views and perspectives on eye movement data collected during code reading tasks when writing computer programs. Hence the focus of this work is on code and…
In order to effectively prepare the next generation of IT professionals and systems analysts, it is important to incorporate cloud based online collaboration tools into the coursework for developing the students' cooperative skills as well…
Recently, large language models (LLMs) have demonstrated excellent performance, inspiring researchers to explore their use in automating register transfer level (RTL) code generation and improving hardware design efficiency. However, the…
Software developers frequently reuse source code from repositories as it saves development time and effort. Code clones accumulated in these repositories hence represent often repeated functionalities and are candidates for reuse in an…
In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use external…
Despite the availability of refactoring as a feature in popular IDEs, recent studies revealed that developers are reluctant to use them, and still prefer the manual refactoring of their code. At JetBrains, our goal is to fully support…