Vincent Siu
RandomMan0880
AI & ML interests
None yet
Recent Activity
new activity
about 2 months ago
WangResearchLab/SteeringSafety:Specify perspectives in README
upvoted
a
paper
3 months ago
COSMIC: Generalized Refusal Direction Identification in LLM Activations
upvoted
a
paper
3 months ago
RepIt: Representing Isolated Targets to Steer Language Models
Organizations
