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 20 days ago
SWE-Explore: Benchmarking How Coding Agents Explore Repositories upvoted a paper 21 days ago
On the Geometry of On-Policy Distillation upvoted a paper 21 days ago
SPACENUM: Revisiting Spatial Numerical Understanding in VLMsOrganizations
None yet
Add task category, paper, and code links to dataset card
#2 opened 7 months ago
by 
nielsr
commented a
paper 7 months ago
commented a
paper about 1 year ago