Xianglong Liu

Learn effective methods to quantize LLMs while maintaining accuracy and performance.

A new technique exposes vulnerabilities in advanced AI systems combining images and text.

New benchmark assesses gender bias in AI models related to job roles.

A new framework enhances diffusion models' efficiency while preserving image quality.

A new method for better database query performance using indexing techniques.

Learn how low-bit quantization improves the efficiency of large language models.

A database to combat backdoor defects in deep learning models.