Related papers: Impermanent Identifiers: Enhanced Source Code Comp…

The recent breakthrough of large language models (LLMs) in natural language processing has sparked exploration in recommendation systems, however, their limited domain-specific knowledge remains a critical bottleneck. Specifically, LLMs…

Many applications can benefit from personalized image generation models, including image enhancement, video conferences, just to name a few. Existing works achieved personalization by fine-tuning one model for each person. While being…

Researchers develop models to explain the unknowns. These models typically involve parameters that capture tangible quantities, the estimation of which is desired. Parameter identifiability investigates the recoverability of the unknown…

Large Language Models (LLMs) exhibit remarkable code generation capabilities but falter when adapting to frequent updates in external library APIs. This critical limitation, stemming from reliance on outdated API knowledge from their…

The complexity and size increase of software has extended the delay for developers as they wait for code analysis and code merge. With the larger and more complex software, more developers nowadays are developing software with large source…

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…

Software developers and maintainers need to read and understand source programs and other software artifacts. The increase in size and complexity of software drastically affects several quality attributes, especially understandability and…

Continuous integration (CI) tools integrate code changes by automatically compiling, building, and executing test cases upon submission of code changes. Use of CI tools is getting increasingly popular, yet how proprietary projects reap the…

Modern software systems continuously undergo code upgrades to enhance functionality, security, and performance, and Large Language Models (LLMs) have demonstrated remarkable capabilities in code migration tasks. However, while research on…

This study aims to enhance the maintainability of code generated by Large Language Models (LLMs), with a focus on the Python programming language. As the use of LLMs for coding assistance grows, so do concerns about the maintainability of…

An essential part of software maintenance and evolution, refactoring is performed by developers, regardless of technology or domain, to improve the internal quality of the system, and reduce its technical debt. However, choosing the…

Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance code remains limited--a critical requirement in real-world software systems. We argue that current…

The development of services and the growing demand for resources sharing among users from different organizations with some level of affinity have motivated the creation of Identity Management Systems. Identity Management has gained…

Code reviews are a critical yet time-consuming aspect of modern software development, increasingly challenged by growing system complexity and the demand for faster delivery. This paper presents a study conducted at WirelessCar Sweden AB,…

DNA sequence analysis is fundamental to life science research. The rapid development of next generation sequencing (NGS) technologies, and the richness and diversity of applications it makes feasible, have created an enormous gulf between…

The code base of software projects evolves essentially through inserting and removing information to and from the source code. We can measure this evolution via the elements of information - tokens, words, nodes - of the respective…

Background: Developers spend a lot of their time on understanding source code. Static code analysis tools can draw attention to code that is difficult for developers to understand. However, most of the findings are based on non-validated…

In this paper, we generalize the well-known index coding problem to exploit the structure in the source-data to improve system throughput. In many applications, the data to be transmitted may lie (or can be well approximated) in a…

Introduction: Digital products increasingly reshape industries, influencing human behavior and decision-making. However, the software development teams developing these systems often lack diversity, which may lead to designs that overlook…

Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…