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 person has tousled brown hair and expressive blue eyes, their posture confident and relaxed as they hold the reins with steady hands
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.