Posterior Flow Matching：一种可输出端点不确定性的生成建模框架

Posterior Flow Matching

AI 导读

研究者提出 Posterior Flow Matching（PFM），用高斯后验模型同时学习条件速度均值与逐分量方差，使单次模型评估即可给出传输预测和端点不确定性。该方法支持均值驱动的 ODE 与后验驱动的 SDE，后者局部噪声尺度随预测不确定性自适应调整。在图像、点云、分子和动作生成任务上，PFM 提升了生成质量，并可在整个生成过程中读取端点后验信息。

正文 · 原文

View PDF HTML (experimental)

Abstract:Flow matching learns how to transport noise toward data, but its mean prediction does not directly report the endpoint uncertainty remaining at an intermediate state. This paper introduces Posterior Flow Matching (PFM), a general generative modeling framework that learns conditional velocity means and componentwise variances with a Gaussian posterior model. The same model evaluation supplies both a transport prediction and endpoint uncertainty, making posterior diagnostics available throughout generation. These learned moments support a mean-driven ordinary differential equation (ODE) and a posterior-driven stochastic differential equation (SDE), whose local noise scales adapt to the predicted uncertainty. Across image, point-cloud, molecular, and action generation, PFM improves generation quality and provides endpoint-posterior readouts throughout generation.

Subjects:	Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
Cite as:	arXiv:2610.13994 [cs.LG]
	(or arXiv:2610.13994v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.13994 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Chenrui Ma [view email]
[v1] Sat, 26 Sep 2026 20:44:52 UTC (30,029 KB)

来源：arXiv cs.AI · arxiv.org