Xin Peng

Study explores static analysis to enhance repository-level code completion.

Examining the impact of deprecated APIs on LLM code suggestions.

A new approach combines knowledge and technology to improve software vulnerability detection.

A two-stage framework improves Python's type inference, enhancing code quality and efficiency.

A new system enhances code translation accuracy and efficiency using specialized agents.

Creating diverse road setups improves safety testing for self-driving vehicles.