奖励其实一直都在你的数据中：通过判别器引导的强化学习来修正流匹配问题
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
摘要
分数和流匹配模型通常依赖基于偏好的强化学习来实现两个目的：一是符合主观偏好，二是获取诸如视觉真实性和物体结构一致性等属性——这些属性本应通过数据本身来学习。我们认为，这种做法实际上反映了一种结构上的不匹配。匹配损失用于衡量训练时刻下速度或分数场上的ell_2回归误差，而这一指标与判断样本质量时所需的视觉和语义属性并不一致。如果有一个与这些属性相一致的奖励机制，那么强化学习就可以避免这种不匹配，因为它可以直接根据模型自身的样本来评估模型性能，从而遵循奖励机制。挑战在于如何在不依赖人类偏好的情况下获得这样的奖励——因为人类的偏好往往难以准确捕捉，而且还会让数据的真实性与标注人的倾向混为一谈。 我们提出了“鉴别器引导强化学习”方法。该方法训练一个鉴别器，使其能够在预训练的表示空间中将数据与基础模型样本区分开来，并将该鉴别器的logit作为KL正则化强化学习中的奖励。预训练空间限制了鉴别器的感知意义方向，而logit则估计了数据与模型之间的对数似然比，这是针对数据分布的最佳奖励方式。在SiT、JiT、REPA和RAE模型中，DRL都能降低无引导情况下的FID值（例如，SiT上的FID从9.38降至2.62），同时还能改善语义空间的FD值（例如，DINOv3上的FD从88.2降至19.3）。在所有模型中都取得了类似的改进效果，而且无需对模型进行训练即可获得符合人类偏好的奖励。此外，在基于偏好的后期处理过程中，DRL还能使偏好奖励与图像质量之间达到更好的平衡，从而提升图像质量，同时减少过饱和和过度亮度等低级问题。
English Abstract
Score- and flow-matching models often rely on preference-based reinforcement learning for two purposes: aligning with subjective preferences and, surprisingly, recovering properties such as visual realism and coherent object structure that matching-based training is intended to learn from the data itself. We argue that this reflects a structural mismatch. Matching losses measure ell_2 regression error on the velocity or score field under training-time marginals, a proxy poorly aligned with the visual and semantic properties that determine sample quality at inference. Given a reward aligned with these properties, RL sidesteps the mismatch by evaluating the model on its own samples and following the reward landscape directly. The challenge is to obtain such a reward without relying on human preferences, which are expensive and conflate data realism with annotator inclinations. We propose Discriminator-Guided RL (DRL). DRL trains a discriminator to separate data from base-model samples in a pretrained representation space and uses its logit as the reward in KL-regularized RL. The pretrained space restricts the discriminator to perceptually meaningful directions, and the logit estimates the log-likelihood ratio between data and model, which is the optimal reward for targeting the data distribution. Across SiT, JiT, REPA, and RAE, DRL reduces guidance-free FID (e.g., 9.38 to 2.62 on SiT) and semantic-space FD (e.g., 88.2 to 19.3 on DINOv3 for SiT), with consistent gains across all backbones, and improves human-preference rewards without training on them. It also yields a better Pareto frontier between preference reward and image fidelity under subsequent preference-based post-training, increasing alignment while reducing low-level artifacts such as oversaturation and excessive brightness.