Picture for Dingqian Hong

Dingqian Hong

GVPO: Group Variance Policy Optimization for Large Language Model Post-Training

Add code
Apr 28, 2025
Figure 1 for GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
Figure 2 for GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
Figure 3 for GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
Viaarxiv icon