Related papers: KOALA: a Configurable Tool for Collecting IDE Data…

The process of writing code and use of features in an integrated development environment (IDE) is a fruitful source of data in computing education research. Existing studies use records of students' actions in the IDE, consecutive code…

While learning programming languages is crucial for software engineers, mastering the necessary tools is equally important. To facilitate this, JetBrains recently released the JetBrains Academy plugin, which customizes the IDE for learners,…

In very recent years more attention has been placed on probing the role of pre-training data in Large Language Models (LLMs) downstream behaviour. Despite the importance, there is no public tool that supports such analysis of pre-training…

In this work, we introduce a novel approach to programming education - in-IDE courses implemented for IntelliJ-based IDEs via the JetBrains Academy Plugin. The primary objective of this approach is to address the challenge of familiarizing…

The training of large models, involving fine-tuning, faces the scarcity of high-quality data. Compared to the solutions based on centralized data centers, updating large models in the Internet of Things (IoT) faces challenges in…

We present COALA, a vision-centric Federated Learning (FL) platform, and a suite of benchmarks for practical FL scenarios, which we categorize into three levels: task, data, and model. At the task level, COALA extends support from simple…

A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client. To address this, we propose a method Federated learning with Adaptive Local Aggregation (FedALA)…

Compositional reasoning is a hallmark of human visual intelligence. Yet, despite the size of large vision-language models, they struggle to represent simple compositions by combining objects with their attributes. To measure this lack of…

Data heterogeneity is an intrinsic property of recommender systems, making models trained over the global data on the cloud, which is the mainstream in industry, non-optimal to each individual user's local data distribution. To deal with…

We introduce KodCode, a synthetic dataset that addresses the persistent challenge of acquiring high-quality, verifiable training data across diverse difficulties and domains for training Large Language Models for coding. Existing…

Integrated development environments (IDE) support developers in a variety of tasks. Unobtrusively capturing developers' cognitive load while working on different programming tasks could help optimize developers' work experience, increase…

Students often struggle with solving programming problems when learning to code, especially when they have to do it online, with one of the most common disadvantages of working online being the lack of personalized help. This help can be…

Software developers use metrics to evaluate code quality and productivity, but these practices are still rare in programming education. This project bridges the gap by collecting real-time learning analytics from individual student and…

A great part of software development involves conceptualizing or communicating the underlying procedures and logic that needs to be expressed in programs. One major difficulty of programming is turning concept into code, especially when…

Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full potential remains unexplored. In this paper, we introduce…

Integrated development environments (IDEs) are prevalent code-writing and debugging tools. However, they have yet to be widely adopted for launching machine learning (ML) experiments. This work aims to fill this gap by introducing JetTrain,…

Deep learning (DL)-based code completion tools have transformed software development by enabling advanced code generation. These tools leverage models trained on vast amounts of code from numerous repositories, capturing general coding…

In software engineering, it is not enough to simply write code that only works as intended, even if it is free from vulnerabilities and bugs. Every programming language has a style guide and a set of best practices defined by its community,…

AI-enabled features built on LLMs and agentic workflows are difficult to test, debug, and reproduce, especially for product-focused software engineers without a machine learning background. We present the AI Toolkit plugin for JetBrains…

In recent years, several industrial solutions for the problem of multi-token code completion appeared, each making a great advance in the area but mostly focusing on cloud-based runtime and avoiding working on the end user's device. In this…