AI 中文总结
该研究提出无需训练的闭环控制器RACER，利用预测分歧信号调整对扩散特征预测的信任度，在多模型多数据集上实现了相同评估次数下的性能提升或同等质量下的更快采样。
AI 中文摘要
无需训练的特征预测通过预测跳过去噪步骤的特征来加速扩散采样，近期研究主要聚焦于设计更强的预测器。然而，不同步骤的预测误差差异显著，开环缓存会在每个跳过步骤中完全信任预测结果，当加速力度过大时，这种固定信任机制会失效。被忽略的问题不仅是如何更好地预测，还包括何时以及在多大程度上信任预测结果。我们发现，可从缓存本身观测到预测可靠性：当特征轨迹平滑时，两个预测结果一致；当预测难度增大时，二者会产生分歧。这种分歧是一种低成本的运行时信号，无需额外去噪器评估。基于该信号，我们提出RACER，这是一种无需训练的闭环控制器，包含两种响应机制：它会持续将不确定的预测结果向最后计算出的特征收缩；在风险最高的步骤中，RACER会刷新特征，通过跳过后续计划的一次评估来抵消新增评估的开销。我们推导了收缩操作的确定性误差边界，并在不同加速区间对其有效性和紧密度进行了实证评估。在相同去噪器评估次数下，RACER在DrawBench、VBench和COCO数据集上，针对SD3.5-Large、FLUX.1-dev、Wan2.1-14B和HunyuanVideo模型，均优于最强的开环基线；在SD3.5模型上，还能在同等质量下实现更快采样。RACER对不同预测设计具有通用性，例如，它可恢复Taylor基预测器丢失的大部分质量。这些结果表明，可靠的扩散加速还取决于预测结果的使用方式。代码可在https URL获取。
英文摘要
Training-free feature forecasting accelerates diffusion sampling by predicting features at skipped denoising steps. Recent work has mainly focused on designing stronger forecasters. Yet forecast error varies sharply across steps, and open-loop caches trust the forecast in full at every skipped step. This fixed trust is what breaks as acceleration turns aggressive. The missing question is not only how to forecast better, but when and how much to trust a forecast. We show that reliability can be observed from the cache itself. Two forecasts agree where the feature trajectory is smooth, and they diverge where prediction turns hard. Their disagreement is a cheap runtime signal, and it costs no extra denoiser evaluation. Based on this signal, we introduce RACER, a training-free closed-loop controller with two responses. It continuously shrinks uncertain forecasts toward the last computed feature. At the riskiest steps, RACER refreshes the feature and repays the added evaluation by skipping a later scheduled one. We derive a deterministic error bound for the shrinkage and empirically evaluate its validity and tightness across acceleration regimes. At the same number of denoiser evaluations, RACER improves the strongest open-loop baseline across SD3.5-Large, FLUX.1-dev, Wan2.1-14B, and HunyuanVideo on DrawBench, VBench, and COCO. On SD3.5, we further show that RACER samples faster at equal quality. RACER generalizes across forecasting designs as well. For example, it recovers much of the quality lost on a Taylor base. These results show that reliable diffusion acceleration also depends on how forecasts are used. Code is available at https://github.com/LiZaiyuan0619/RACER
