Flash-GRPO introduces iso-temporal grouping and temporal gradient rectification to enable single-step GRPO training that outperforms full-trajectory methods on video diffusion alignment under low compute budgets.
The zebra has distinctive black and white stripes, while the giraffe boasts a long neck and spotted coat
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
Flash-GRPO introduces iso-temporal grouping and temporal gradient rectification to enable single-step GRPO training that outperforms full-trajectory methods on video diffusion alignment under low compute budgets.