CVApr 5

OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models

arXiv:2604.0414271.92 citations
AI Analysis

This addresses a training efficiency problem for researchers and practitioners using flow-matching models, representing an incremental improvement over existing methods.

The paper tackled the low sample efficiency of GRPO in flow-matching models by introducing OP-GRPO, an off-policy framework that uses a replay buffer and importance sampling, achieving comparable or superior performance with only 34.2% of the training steps on average.

Post training via GRPO has demonstrated remarkable effectiveness in improving the generation quality of flow-matching models. However, GRPO suffers from inherently low sample efficiency due to its on-policy training paradigm. To address this limitation, we present OP-GRPO, the first Off-Policy GRPO framework tailored for flow-matching models. First, we actively select high-quality trajectories and adaptively incorporate them into a replay buffer for reuse in subsequent training iterations. Second, to mitigate the distribution shift introduced by off-policy samples, we propose a sequence-level importance sampling correction that preserves the integrity of GRPO's clipping mechanism while ensuring stable policy updates. Third, we theoretically and empirically show that late denoising steps yield ill-conditioned off-policy ratios, and mitigate this by truncating trajectories at late steps. Across image and video generation benchmarks, OP-GRPO achieves comparable or superior performance to Flow-GRPO with only 34.2% of the training steps on average, yielding substantial gains in training efficiency while maintaining generation quality.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes