Xiaofei Ma

A new framework enhances output quality for language models in open-ended tasks.

A new method enhances test generation using large language models for better coverage.

A new method improves code understanding through extensive data and training techniques.

A new method improves code completion by reducing unnecessary information retrieval.

Enhancing code generation models to handle minor input changes effectively.

Enhancing LLMs' ability to refine their code through self-debugging techniques.