SOURCE-LINKED INTELLIGENCE

Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree Coupling

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

The performance of Flow Matching largely depends on the quality of the coupling between the source and target distributions. However, independent coupling often leads to path crossings and local velocity ambiguity, while OT-based couplings typically incur high construction costs. To address this challenge, we propose Quantile AlignTree Flow Matching (QAT-FM), an efficient structured coupling strategy that constructs a hierarchical coupling between a Gaussian prior and the target data distribution via a quantile-aligned tree structure. QAT-FM constructs the coupling in $\mathcal{O}(Nd\log N)$ t

Read original source ↗ Open in workspace

recordType

paper

region

Global