Densegrpo Flow Matching

Improve diffusion model alignment by assigning step-wise rewards during denoising instead of terminal rewards. Fixes sparse reward signal mismatch in multi-step generation processes through ODE-based reward estimation.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit de1f811de8

Frequently asked questions

npx get-skill add adu2021/densegrpo-flow-matching