Saved in:
Bibliographic Details
Main Authors: Tsakonas, Constantinos, Ivaldi, Serena, Mouret, Jean-Baptiste
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.13061
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918336938377216
author Tsakonas, Constantinos
Ivaldi, Serena
Mouret, Jean-Baptiste
author_facet Tsakonas, Constantinos
Ivaldi, Serena
Mouret, Jean-Baptiste
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_13061
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Diverging Flows: Detecting Extrapolations in Conditional Generation
Tsakonas, Constantinos
Ivaldi, Serena
Mouret, Jean-Baptiste
Machine Learning
Artificial Intelligence
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.
title Diverging Flows: Detecting Extrapolations in Conditional Generation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.13061