发表机构
University of Science and Technology of China（中国科学技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出混合基特征预测框架，通过多基函数融合与自适应权重，在无需训练的情况下加速扩散采样，并在多个模型上实现质量与速度的有利权衡。
AI 中文摘要
我们提出了混合基特征预测（HybridFF），一个无需训练、即插即用的框架，用于加速扩散采样。为了在建模特征演化时捕捉局部平滑性、长程趋势和复杂的非单调变化，HybridFF 首先使用移动最小二乘法（MLS）为多个互补的基函数族分别估计系数，然后使用融合权重组合相应的预测器。除了基函数的选择，融合权重也起着关键作用。我们引入了两种策略来平衡质量与加速效果。HybridFF（固定）通过在小规模数据集上校准的模型特定融合权重优先考虑效率，并在推理过程中保持这些权重不变。HybridFF（自适应）使用从全步预测误差的指数移动平均计算的分支可靠性分数在线更新融合权重，在激进缓存下提高预测保真度和生成质量，同时保持显著的加速效果。在 DiT-XL/2、FLUX.1-dev、SD3.5-Large 和 HunyuanVideo 上的实验表明，与代表性的单基预测器和缓存基线相比，该方法在加速与质量之间取得了有利的权衡。
英文摘要
We propose Hybrid-Basis Feature Forecasting (HybridFF), a training-free, plug-and-play framework for accelerating diffusion sampling. To capture local smoothness, long-range trends, and complex non-monotonic variations when modeling feature evolution, HybridFF first estimates coefficients using moving least squares (MLS) for each of multiple complementary basis families and then combines the corresponding predictors using fusion weights. In addition to the choice of basis functions, the fusion weights also play a critical role. We introduce two strategies to balance quality and speedup. HybridFF (Fixed) prioritizes efficiency with model-specific fusion weights calibrated on a small set and held constant during inference. HybridFF (Adaptive) updates the fusion weights online using branch reliability scores computed from an exponential moving average of full-step prediction errors, improving prediction fidelity and generation quality under aggressive caching while retaining substantial acceleration. Experiments across DiT-XL/2, FLUX.1-dev, SD3.5-Large, and HunyuanVideo demonstrate a favorable speedup--quality trade-off over representative single-basis forecasters and caching baselines.
