SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
Paper
•
2512.02807
•
Published
•
8
zhihao
ust-zzh
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
updated
a Space
5 months ago
TDDBench/README
published
a Space
6 months ago
TDDBench/demo
Organizations
upvoted
a
paper
about 1 month ago