SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
Paper • 2511.12982 • Published • 4 •
2
Xuankun Rong
XuankunRong
AI & ML interests
AI Safety
Recent Activity
upvoted a paper 8 days ago
Do LLMs Know Their Vulnerable Scenarios? upvoted a paper 11 days ago
Progress Reward Modeling for Robotic Learning: A Comprehensive Survey liked a dataset 22 days ago
XuankunRong/SafeTag-VL-3KOrganizations
None yet
Add task category, paper, and code links to dataset card
#2 opened 9 months ago
by 
nielsr
commented a
paper 9 months ago
commented a
paper about 1 year ago