SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment

SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment

2 December 2025

Yixuan Tang

Yi Yang

ArXiv (abs)PDF HTML

Papers citing "SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment"

0 / 0 papers shown

Title
No papers found