Zixuan Weng
YukinoAsuna
AI & ML interests
None yet
Recent Activity
authored a paper about 20 hours ago
Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMs authored a paper about 20 hours ago
Foot-In-The-Door: A Multi-turn Jailbreak for LLMs upvoted a paper about 21 hours ago
Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMsOrganizations
None yet