Rui Wen

Custom LLMs raise safety concerns, particularly with instruction backdoor attacks.

Diverse samples enhance the effectiveness of machine learning model theft.

Investigating how magnetic fields influence quarks and pions in extreme conditions.

Competition reveals vulnerabilities and defenses in language model security.

Research on twisted MoTe reveals new prospects for quantum memory storage.

Exploring unique phases of quantum materials and their implications for research.

Examining how important data points attract more security risks in machine learning.

Exploring the mysterious behaviors of particles under extreme conditions.