Quanjun Zhang

Research highlights pre-trained models' effectiveness in fixing software vulnerabilities.

A novel approach to fixing software bugs using language models for donor code selection.

A new method enhances machine translation testing for better accuracy.

Exploring how Large Language Models are transforming software bug fixing.

Discover how TestART improves automated unit test generation.

Introducing LRP4RAG, a method to better detect hallucinations in language models.

A new framework combines code search, generation, and repair for efficient programming.

GPT-O1 model shows improved bug fixing capabilities compared to earlier versions.

This article assesses how well LLMs generate test cases for Java programs.

Discover how LLMs transform unit testing for developers.