Amft Meta Learning Alignment

Use meta-learning to automatically balance Supervised Fine-Tuning and Reinforcement Learning signals, treating SFT and RL as complementary rewards in a unified single-stage training framework.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 4c701eb378

Frequently asked questions

npx get-skill add adu2021/amft-meta-learning-alignment