Juan Zhai

This study evaluates LCGMs' performance on coding tasks in English and Chinese.

MaxLin improves CNN verification accuracy and efficiency for safer AI applications.

A new method finds performance bugs in DL frameworks efficiently.

A new tool aims to identify vulnerabilities in cross-chain smart contracts.

A new framework tackles fairness in deep neural networks during model pruning.

A new method enhances jailbreaking efficiency and effectiveness in large language models.