LVLM Safety
Xuankun Rong
XuankunRong
AI & ML interests
AI Safety
Recent Activity
upvoted
a
paper
about 12 hours ago
Your Group-Relative Advantage Is Biased
upvoted
a
paper
about 2 months ago
Latent Collaboration in Multi-Agent Systems
authored
a paper
about 2 months ago
SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
Organizations
None yet
models
0
None public yet