TFTF：无训练目标流用于条件采样
TFTF: Training-Free Targeted Flow for Conditional Sampling
AI总结：
TFTF通过引入随机流和重采样技术，实现无训练条件采样，提升高维和多模态场景下的生成效果。
摘要：
我们提出了一种基于重要性采样的重要性采样方法，用于流匹配模型的无训练条件采样。由于简单应用重要性采样在高维设置中会导致权重退化，我们在生成过程的中间阶段引入了序列蒙特卡罗（SMC）中的重采样技术。为了鼓励生成样本沿着不同的轨迹扩散，我们推导出一种具有可调噪声强度的随机流，以替代中间阶段的确定性流。我们的框架无需额外训练，同时提供了渐近准确性的理论保证。实验表明，我们的方法在MNIST和CIFAR-10的条件采样任务中显著优于现有方法。我们进一步通过CelebA-HQ上的文本到图像生成实验，展示了我们的方法在高维、多模态设置中的适用性。
英文摘要：
We propose a training-free conditional sampling method for flow matching models based on importance sampling. Because a naïve application of importance sampling suffers from weight degeneracy in high-dimensional settings, we modify and incorporate a resampling technique in sequential Monte Carlo (SMC) during intermediate stages of the generation process. To encourage generated samples to diverge along distinct trajectories, we derive a stochastic flow with adjustable noise strength to replace the deterministic flow at the intermediate stage. Our framework requires no additional training, while providing theoretical guarantees of asymptotic accuracy. Experimentally, our method significantly outperforms existing approaches on conditional sampling tasks for MNIST and CIFAR-10. We further demonstrate the applicability of our approach in higher-dimensional, multimodal settings through text-to-image generation experiments on CelebA-HQ.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
