MUSE

AI & ML interests

Machine unlearning evaluation benchmark

Recent Activity

swj0419  authored a paper 20 days ago

Negative Token Merging: Image-based Adversarial Feature Guidance

yangsibo  authored a paper about 2 months ago

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

yangsibo  authored a paper about 2 months ago

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models

View all activity

Team members 3