ICML2026 paper: "Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment"
Xiaoyu Wen
XiaoyuWen
AI & ML interests
None yet
Recent Activity
updated a dataset about 1 month ago
XiaoyuWen/PIA-Persona-Dataset updated a collection about 1 month ago
PIA updated a collection about 1 month ago
PIA