Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcement learning remains largely unexplored. We observe that naively applying GRPO to UDM leads to training instability and marginal performance gains. To address this, we propose \Ours, the first framework to integrate UDM with RL. Our method is guided by two key insights: (i) treating the final clean sample as the action provides more accurate and stable optimization signals; and (ii) reconstructing trajectories via the diffusion forward process better aligns probability paths with the pretraining distribution. Additionally, we introduce two strategies, Reduced-Step and CFG-Free, to further improve training efficiency. \Ours significantly improves base model performance across multiple T2I tasks. Notably, GenEval accuracy improves from $69\%$ to $96\%$ and PickScore increases from $20.46$ to $23.81$, achieving state-of-the-art performance in both continuous and discrete settings. On the OCR benchmark, accuracy rises from $8\%$ to $57\%$, further validating the generalization ability of our method. Code is available at \href{https://github.com/Yovecent/UDM-GRPO}{https://github.com/Yovecent/UDM-GRPO}.

翻译：均匀离散扩散模型（UDM）近期已成为离散生成建模领域一种前景广阔的新范式，然而其与强化学习的结合仍鲜有探索。我们观察到，将GRPO直接应用于UDM会导致训练不稳定且性能提升有限。针对这一问题，我们提出了\Ours，这是首个将UDM与强化学习融合的框架。该方法基于两个关键洞察：（i）将最终干净样本作为动作，可提供更准确、更稳定的优化信号；（ii）通过扩散前向过程重构轨迹，能更好地使概率路径与预训练分布对齐。此外，我们引入了“简化步数”（Reduced-Step）与“无无分类器指导”（CFG-Free）两种策略，以进一步提升训练效率。\Ours在多个文本到图像（T2I）任务上显著提升了基模型性能。特别地，GenEval准确率从69%提升至96%，PickScore从20.46提升至23.81，在连续与离散设置下均达到了最先进水平。在OCR基准测试中，准确率从8%提升至57%，进一步验证了本方法的泛化能力。代码已开源：\href{https://github.com/Yovecent/UDM-GRPO}{https://github.com/Yovecent/UDM-GRPO}。