A new benchmark tests LLMs' ability to find software vulnerabilities.
― 5 min read
Computer Science - Software Engineering
RSSLUNAR simplifies log parsing without requiring labeled data, enhancing accuracy and efficiency.
― 7 min read
New framework enhances code completion by capturing repository-specific knowledge.
― 7 min read
A look at vulnerabilities and solutions for deep learning systems.
― 6 min read
Combining fuzzing and language models to improve software testing efficiency.
― 4 min read
DafnyBench benchmarks software verification tools, paving the way for reliable programming.
― 5 min read
A look into how LLMs tackle programming by example challenges.
― 5 min read
Testing LLMs is essential for safe and effective AI applications.
― 6 min read
A new tool improves static analysis with simplified graphs and machine learning.
― 7 min read
A new approach enhances testing reliability for deep learning libraries.
― 6 min read
Learn how data centers measure and report their carbon emissions effectively.
― 6 min read
AlabOS streamlines workflows for automated labs, improving efficiency in materials research.
― 7 min read
Large language models improve differential testing in software development.
― 7 min read
Explore how AI is transforming software engineering practices and roles.
― 10 min read
Study explores static analysis to enhance repository-level code completion.
― 7 min read
This study evaluates how LLMs can enhance mutation testing in software development.
― 5 min read
Examining the impact of deprecated APIs on LLM code suggestions.
― 7 min read
Exploring how GenAI influences software engineering practices and what remains unchanged.
― 7 min read
A system using Agile principles to enhance software development efficiency and collaboration.
― 6 min read
A new approach combines knowledge and technology to improve software vulnerability detection.
― 7 min read
AI streamlines class diagram creation, increasing efficiency and accuracy in software design.
― 6 min read
This article discusses recent developments to improve efficiency in Large Language Models.
― 6 min read
A new method enhances testing speed and fault detection in quantum programs.
― 5 min read
A new method to improve safety tests for autonomous vehicles through generated scenarios.
― 6 min read
A new method finds performance bugs in DL frameworks efficiently.
― 6 min read
Examining the limitations of large language models in understanding code relationships.
― 7 min read
RepoExec evaluates code generation performance at the repository level.
― 6 min read
A framework improves code generation for specialized languages using documentation.
― 7 min read
Addressing the cold start problem with new profiling techniques for better app performance.
― 5 min read
A new tool uses machine learning to detect performance bugs effectively.
― 4 min read
Examining memorization in code completion models and its privacy implications.
― 7 min read
A new dual-transformer model enhances execution time predictions from source code analysis.
― 6 min read
A study on Copilot's ability to generate code across various programming languages.
― 6 min read
This article explores methods to calculate ground state energy using quantum programming.
― 7 min read
A new dataset improves code search efficiency for developers using natural language queries.
― 6 min read
Investigating social annotation's impact on programming students' engagement and performance.
― 10 min read
New methods enhance predictions by focusing on code functionality instead of variable names.
― 6 min read
A tool using AI helps identify key configuration settings for software performance.
― 6 min read
A look into scenario-based testing for evaluating code generation models.
― 8 min read
This benchmark evaluates multimodal models on BPM tasks like documentation and improvement.
― 6 min read