Conditional Flow Matching (CFM) models can generate high-quality samples from a non-informative prior, but they can be slow, often needing hundreds of network evaluations (NFE). To address this, we propose Implicit Dynamical Flow Fusion (IDFF); IDFF learns a new vector field with an additional momentum term that enables taking longer steps during sample generation while maintaining the fidelity of the generated distribution. Consequently, IDFFs reduce the NFEs by a factor of ten (relative to CFMs) without sacrificing sample quality, enabling rapid sampling and efficient handling of image and time-series data generation tasks. We evaluate IDFF on standard benchmarks such as CIFAR-10 and CelebA for image generation, where we achieve likelihood and quality performance comparable to CFMs and diffusion-based models with fewer NFEs. IDFF also shows superior performance on time-series datasets modeling, including molecular simulation and sea surface temperature (SST) datasets, highlighting its versatility and effectiveness across different domains.\href{https://github.com/MrRezaeiUofT/IDFF}{Github Repository}

翻译：条件流匹配（CFM）模型能够从非信息性先验中生成高质量样本，但其采样速度较慢，通常需要数百次网络前向评估（NFE）。为解决此问题，我们提出了隐式动态流融合（IDFF）方法。IDFF通过引入额外的动量项学习一个新的向量场，使得在样本生成过程中能够采用更长的步长，同时保持生成分布的保真度。因此，IDFF在保证样本质量的前提下，将NFE需求降低至CFM的十分之一，从而实现了快速采样并高效处理图像与时间序列数据生成任务。我们在CIFAR-10和CelebA等标准图像生成基准上评估IDFF，结果表明其似然估计与生成质量性能与CFM及基于扩散的模型相当，但所需NFE更少。IDFF在时间序列数据集建模（包括分子模拟和海表面温度数据集）中也表现出优越性能，凸显了其在不同领域的通用性与有效性。\href{https://github.com/MrRezaeiUofT/IDFF}{Github 仓库}