让生成模型快速适配新分布，无需重新训练。
A Flow Matching Algorithm for Many-Shot Adaptation to Unseen Distributions
- 用基函数表示不同分布的生成速度场，通过投影实现快速适配。
- 在未见分布上精度和召回率显著优于基线，尤其在图像数据上表现突出。
- 适合需要快速响应新数据分布的研究者或工业应用。
尽管生成建模在自然语言条件图像生成等任务中取得显著进展，但基于示例数据点进行模型适配仍是一个相对未被充分探索且具有挑战性的问题。为此，我们提出函数投影流匹配（FP-FM），直接以目标分布的样本为条件进行生成。FP-FM学习一组基函数来覆盖一组训练分布对应的速率场，并通过简单的最小二乘投影将模型适配到新分布。该方法可在推理时无需额外训练的情况下，高效生成来自多种目标分布的样本。我们还引入了多个变体，通过丰富系数计算方式（如使系数依赖于时间）在表达能力与计算开销间实现权衡。实验表明，FP-FM在合成数据和图像数据集上均显著提升精度与召回率，尤其在未见分布上表现优异。
原文摘要 · Abstract (English)
While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation from example data points remains a relatively underexplored and challenging problem. To this end, we propose Function Projection for Flow Matching (FP-FM), an algorithm that directly conditions generation on samples from the target distribution. FP-FM learns basis functions to span the velocity fields corresponding to a set of training distributions, and adapts to new distributions by computing a simple least-squares projection onto this basis. This enables efficient generation of samples from diverse target distributions without additional training at inference time. We further introduce multiple variants of FP-FM that provide a trade-off in expressivity and compute by enriching the coefficient calculation, e.g., by making the coefficients dependent on time. FP-FM achieves greatly improved precision and recall relative to baselines across synthetic and image-based datasets, with especially strong gains on unseen distributions.
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。