SOURCE-LINKED INTELLIGENCE

Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Understanding which training samples influence a generated image is an important problem in generative modeling. In flow matching, training samples influence the generated image through the velocity field along the generation trajectory. Removing samples to examine their counterfactual influence changes the velocity field, and the resulting effect on the final image depends on how the change propagates through the trajectory. Consequently, local changes in the velocity field do not necessarily predict the final counterfactual effect. This work investigates attribution in flow-matching models t

Read original source ↗ Open in workspace

recordType

paper

region

Global