用重心有理函数预测扩散模型特征，提升高速推理稳定性。
BRACE: Taming Sharp Irregularities via Barycentric Rational Forecasting for Fast Diffusion Transformers Inference
- 用历史特征直接构建有理函数预测，避免导数不稳问题
- 在多种扩散模型上实现最优画质与速度平衡
- 适合追求高效高保真图像生成的开发者使用
扩散变压器（DiTs）在高质量图像和视频生成中表现出色。为缓解其巨大的计算开销，已有研究提出通过缓存时序特征来跳过冗余计算。然而，现有基于导数的多项式预测方法在高加速比下常因长步预测不稳定导致质量严重下降。为此，本文提出带有切比雪夫增强的重心有理预测（BRACE）。受观察启发：尽管DiT特征轨迹整体平滑，但常存在尖锐不规则和局部非光滑现象，BRACE将范式从导数驱动的多项式外推转为特征驱动的有理预测。具体地，它维护一个局部滑动窗口以缓存稀疏的历史特征，并利用改进的切比雪夫权重构建重心有理函数，直接聚合原始特征以保证数值稳定性。大量实验表明，BRACE在各类DiT架构上均实现当前最优的质量-效率权衡，且计算开销可忽略不计。
原文摘要 · Abstract (English)
Diffusion Transformers (DiTs) have demonstrated exceptional performance in high-fidelity image and video generation. To alleviate their massive computational overhead, temporal feature caching has been proposed to bypass redundant computations. However, existing cache-then-forecast methods driven by derivative-based polynomials often cause severe quality degradation under high acceleration due to unstable long-step predictions. To address this bottleneck, we propose Barycentric Rational Forecasting with Chebyshev Enhancement (BRACE). Motivated by the observation that DiT feature trajectories are globally smooth yet frequently exhibit sharp irregularities and local non-smoothness, BRACE shifts the paradigm from derivative-driven polynomial extrapolation to feature-driven rational forecasting. Specifically, it maintains a local sliding window to cache sparse historical features and leverages adapted Chebyshev weights to formulate a barycentric rational function, directly aggregating these raw features to ensure numerical stability. Extensive experiments demonstrate that BRACE achieves state-of-the-art quality-efficiency trade-offs across various DiT architectures with negligible computational overhead.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。