University of Washington

AI & ML interests

None defined yet.

Recent Activity

LNIU  authored a paper about 1 month ago

ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates

LNIU  authored a paper about 1 month ago

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

LNIU  authored a paper about 1 month ago

Stronger Models are NOT Stronger Teachers for Instruction Tuning

View all activity

Team members 694