G2RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance

community

https://github.com/T-Lab-CUHKSZ/G2RPO-A

AI & ML interests

None defined yet.

Recent Activity

Blancy updated a dataset about 2 months ago

G2RPO-A/Code-CoT

Blancy updated a dataset about 2 months ago

G2RPO-A/Math-Curriculum-1K

View all activity

updated 2 datasets about 2 months ago

G2RPO-A/Code-CoT

Viewer • Updated Sep 15 • 1.09k • 32

G2RPO-A/Math-Curriculum-1K

Viewer • Updated Sep 14 • 1k • 27