InfoWorld

Meta shows structured prompts can make LLMs more reliable for code review

A new “semi-formal reasoning” approach forces AI models to trace code paths and justify conclusions, improving accuracy while ...
Communications of the ACM

Copiloting the Copilots for Automated Program Repair

During automated (APR), it can be challeng\x02ing to synthesize correct patches for real-world systems in general-purpose ...
Journal of Medical Internet Research

Optimizing Initial Vancomycin Dosing in Hospitalized Patients Using Machine Learning Approach for Enhanced Therapeutic Outcomes: Algorithm Development and Validation Study

Objective: This study aimed to develop and evaluate a machine learning (ML)–based algorithm to predict whether an initial vancomycin dose falls within the therapeutic range of the 24-hour area under ...
IEEE

A Feature-Based Learning Differential Evolution Algorithm for the Flexible Job-Shop Scheduling With Occupational Repetitive Actions Index

Abstract: Learning differential evolution (DE) algorithms are widely adopted to address flexible job-shop scheduling problems (FJSPs) because of the optimization ability. However, traditional learning ...
IEEE

Detection of Vulnerabilities in AI-Generated Java Code Using Random Forest Algorithm

Abstract: The swift integration of AI-powered tools for code generation is transforming the software development process, yielding substantial productivity benefits. Nevertheless, the security of code ...