Dataset distillation compresses large datasets into compact synthetic sets with comparable performance in training models. Despite recent progress on diffusion-based distillation, this type of method typically depends on heuristic guidance or prototype assignment, which comes with time-consuming sampling and trajectory instability and thus hurts downstream generalization especially under strong control or low IPC. We propose \emph{Path-Guided Flow Matching (PGFM)}, the first flow matching-based framework for generative distillation, which enables fast deterministic synthesis by solving an ODE in a few steps. PGFM conducts flow matching in the latent space of a frozen VAE to learn class-conditional transport from Gaussian noise to data distribution. Particularly, we develop a continuous path-to-prototype guidance algorithm for ODE-consistent path control, which allows trajectories to reliably land on assigned prototypes while preserving diversity and efficiency. Extensive experiments across high-resolution benchmarks demonstrate that PGFM matches or surpasses prior diffusion-based distillation approaches with fewer steps of sampling while delivering competitive performance with remarkably improved efficiency, e.g., 7.6$\times$ more efficient than the diffusion-based counterparts with 78\% mode coverage.

翻译：数据集蒸馏将大型数据集压缩为紧凑的合成集，在训练模型时能获得可比的性能。尽管基于扩散的蒸馏方法近期取得了进展，但这类方法通常依赖于启发式引导或原型分配，这伴随着耗时的采样和轨迹不稳定性，从而损害了下游泛化能力，尤其在强控制或低IPC条件下。我们提出了**路径引导流匹配**，这是首个基于流匹配的生成式蒸馏框架，通过求解常微分方程在少数步骤内实现快速确定性合成。PGFM在冻结变分自编码器的潜在空间中进行流匹配，以学习从高斯噪声到数据分布的类别条件传输。特别地，我们开发了一种连续路径到原型引导算法，用于实现ODE一致的路径控制，使轨迹能够可靠地抵达指定的原型，同时保持多样性和效率。在高分辨率基准测试上的大量实验表明，PGFM以更少的采样步骤匹配或超越了先前的基于扩散的蒸馏方法，同时以显著提升的效率提供了具有竞争力的性能，例如，在达到78%模式覆盖率时，其效率比基于扩散的同类方法高出7.6倍。