yxwang
yxwang
AI & ML interests
None yet
Recent Activity
updated
a dataset
7 days ago
yxwang/SafeVid-350K
upvoted
a
paper
16 days ago
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
authored
a paper
about 2 months ago
Fake Alignment: Are LLMs Really Aligned Well?
Organizations
None yet