The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.g., robotics, weather forecasting). However, deployment in safety-critical settings is hindered by a critical extrapolation hazard: driven by smoothness biases, flow models yield plausible outputs even for off-manifold conditions, resulting in silent failures indistinguishable from valid predictions. In this work, we introduce Diverging Flows, a novel approach that enables a single model to simultaneously perform conditional generation and native extrapolation detection by structurally enforcing inefficient transport for off-manifold inputs. We evaluate our method on synthetic manifolds, cross-domain style transfer, and weather temperature forecasting, demonstrating that it achieves effective detection of extrapolations without compromising predictive fidelity or inference latency. These results establish Diverging Flows as a robust solution for trustworthy flow models, paving the way for reliable deployment in domains such as medicine, robotics, and climate science.

翻译：流匹配（Flow Matching，FM）建模复杂条件分布的能力使其成为预测任务（如机器人学、天气预报）的最先进方法。然而，其在安全关键场景中的部署受到一个关键外推风险的阻碍：受平滑性偏置驱动，流模型即使在流形外条件下也会产生看似合理的输出，导致与有效预测无法区分的静默故障。本文提出发散流（Diverging Flows），这是一种新颖方法，通过对流形外输入施加结构化的低效传输，使单个模型能够同时执行条件生成和原生外推检测。我们在合成流形、跨域风格迁移和天气温度预测任务上评估了该方法，证明其能在不损害预测保真度或推理延迟的前提下，有效检测外推情况。这些结果确立了发散流作为可信流模型的稳健解决方案，为在医学、机器人学和气候科学等领域的可靠部署铺平了道路。