KModels enables businesses to easily implement AI models without deep technical knowledge.
― 7 min read
Computer Science - Software Engineering
RSSStudy assesses language models on their ability to generate web application code.
― 6 min read
A study on how cultural values impact software engineers' adoption of LLMs.
― 8 min read
A new framework improves code generation using pair programming principles.
― 8 min read
A new system enhances software development with a flexible, multi-agent approach.
― 7 min read
Exploring how AI enhances the requirements engineering process in software development.
― 3 min read
A new method enables quick state computation of business processes using event logs.
― 5 min read
Explore how large language models assist in software test maintenance.
― 7 min read
Examining how bug bounty programs enhance security in open-source projects.
― 5 min read
Examining how OSS maintainers tackle security challenges effectively.
― 5 min read
Learn how to predict software performance using a new divisive learning framework.
― 6 min read
A new tool offers quick feedback for programming assignments.
― 7 min read
RePlay simplifies building and testing recommender systems for researchers and professionals.
― 5 min read
This article highlights the significance of effective software design in weeding robots.
― 7 min read
Effective requirements engineering is crucial for the success of AI technologies.
― 5 min read
Learn how LLMs automate the summarization of user app reviews.
― 6 min read
Learn to communicate research effectively with structured scientific writing.
― 6 min read
Exploring safety and compliance in AI-driven healthcare technologies.
― 7 min read
Investigating the struggles developers face when creating accessible mobile applications.
― 6 min read
Examining security issues faced by mobile app developers on Stack Overflow.
― 6 min read
Exploring the benefits of a model-driven approach for cybersecurity risk management.
― 6 min read
A novel approach to streamline UI testing for mobile apps using machine learning.
― 9 min read
Learn key strategies for handling shared resources in concurrent programming.
― 5 min read
A new approach enhances symbolic execution in Python using a Large Language Model.
― 6 min read
New method enhances trust and clarity in software verification processes.
― 7 min read
A new method enhances DNN testing by combining feature selection with uncertainty-based prioritization.
― 6 min read
New method enhances product defect detection in manufacturing using deep learning.
― 6 min read
A look into applying MCDC testing metrics in Rust programming.
― 7 min read
This study highlights the risks posed by code clones and their management.
― 7 min read
Study reveals how faulty code affects test case quality from LLMs.
― 5 min read
Harden helps users track behaviors and thoughts to combat addiction.
― 5 min read
Using LLMs for accurate software project cost and duration estimation.
― 7 min read
Inconsistent code comments can lead to bugs and software issues.
― 6 min read
Key points to enhance your NeurIPS paper for better evaluation.
― 4 min read
This study assesses the effectiveness of various LLMs in identifying code vulnerabilities.
― 5 min read
Examining the privacy issues linked to third-party SDKs in mobile applications.
― 4 min read
A new benchmark assessing large code models in real-world coding tasks.
― 5 min read
Analyzing WASI performance issues using an eBPF-based framework for better web applications.
― 6 min read
Explore the causes and solutions for flaky tests disrupting software development.
― 5 min read
GPT-O1 model shows improved bug fixing capabilities compared to earlier versions.
― 6 min read