Deploying GRPO on Flow Matching models has proven effective for text-to-image generation. However, existing paradigms typically propagate an outcome-based reward to all preceding denoising steps without distinguishing the local effect of each step. Moreover, current group-wise ranking mainly compares trajectories at matched timesteps and ignores within-trajectory dependencies, where certain early denoising actions can affect later states via delayed, implicit interactions. We propose TurningPoint-GRPO (TP-GRPO), a GRPO framework that alleviates step-wise reward sparsity and explicitly models long-term effects within the denoising trajectory. TP-GRPO makes two key innovations: (i) it replaces outcome-based rewards with step-level incremental rewards, providing a dense, step-aware learning signal that better isolates each denoising action's "pure" effect, and (ii) it identifies turning points-steps that flip the local reward trend and make subsequent reward evolution consistent with the overall trajectory trend-and assigns these actions an aggregated long-term reward to capture their delayed impact. Turning points are detected solely via sign changes in incremental rewards, making TP-GRPO efficient and hyperparameter-free. Extensive experiments also demonstrate that TP-GRPO exploits reward signals more effectively and consistently improves generation. Demo code is available at https://github.com/YunzeTong/TurningPoint-GRPO.

翻译：在流匹配模型上部署GRPO已被证明对文本到图像生成有效。然而，现有范式通常将基于结果的奖励传播到所有先前的去噪步骤，而未区分每个步骤的局部效应。此外，当前的分组排序主要比较匹配时间步的轨迹，而忽略了轨迹内的依赖关系，其中某些早期去噪动作可能通过延迟的隐式交互影响后续状态。我们提出了TurningPoint-GRPO（TP-GRPO），这是一个缓解逐步奖励稀疏性并显式建模去噪轨迹内长期效应的GRPO框架。TP-GRPO做出了两项关键创新：（i）用步骤级增量奖励替代基于结果的奖励，提供密集的、步骤感知的学习信号，以更好地隔离每个去噪动作的“纯粹”效应；（ii）识别转折点——即翻转局部奖励趋势并使后续奖励演化与整体轨迹趋势一致的步骤——并为这些动作分配聚合的长期奖励，以捕捉其延迟影响。转折点仅通过增量奖励的符号变化检测，使得TP-GRPO高效且无需超参数调整。大量实验也表明，TP-GRPO能更有效地利用奖励信号，并持续提升生成质量。演示代码可在https://github.com/YunzeTong/TurningPoint-GRPO获取。