Generalized Wasserstein Flow Matching: Nested Couplings for Point Cloud Generation
arXiv:2605.08424v3 Announce Type: replace Abstract: We formulate flow matching on probability measures over probability measures. Directly from the Wasserstein-on-Wasserstein (WoW) continuity equation, we show that admissible nested outer and inner couplings induce a valid metameasure flow and non-local velocity field. Validity requires neither optimal plans nor a smooth manifold. Practically, this opens up the design space of multisample flow matching: exact Wasserstein plans are distinguished by energy and straightness, while sliced and lazy linear plans yield scalable alternatives. Point-cloud experiments, including controlled Bures-Wasserstein and Euclidean minibatch baselines, demonstrate the resulting geometry-cost trade-off.
Get stories like this every Monday
The week's most important AI news in one email. Free, unsubscribe anytime.
Score: 2.82
Engagement proxy: 0
Canonical link: https://arxiv.org/abs/2605.08424