TLDR
一步生成器能在单次网络评估下实现高质量视觉生成，但其后训练较为困难：通用隐式生成器既不提供可处理的似然，也不提供去噪轨迹，且许多奖励信号不可微。我们提出 Reward-Weighted Transport Distillation (RWTD)，一种仅依赖生成样本与标量奖励评估的后训练方法。RWTD 并非仅对齐到传统的奖励倾斜参考分布，而是构造一个自适应目标，融合分别倾斜后的当前分布与参考分布。One-step generators enable high-quality visual generation with a single network evaluation, but their post-training is difficult: general implicit generators provide neither tractable likelihoods nor denoising trajectories, and many rewards are non-differentiable. We introduce Reward-Weighted Transport Distillation (RWTD), a post-training method that requires only generated samples and scalar reward evaluations. Rather than aligning solely to the conventional reward-tilted reference distribution, RWTD constructs an adaptive target that mixes separately tilted current and reference distribution