Zixuan Weng

YukinoAsuna

7 3

·

AI & ML interests

None yet

Recent Activity

authored a paper 2 days ago

Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs

authored a paper 2 days ago

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs

upvoted a paper 2 days ago

Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs

View all activity

Organizations

None yet

YukinoAsuna 's models 1

YukinoAsuna/test_trainer

Text Classification • 0.1B • Updated Sep 10, 2024 • 4