Riemannian Wasserstein Entropic Flow Matching (RWEFM) is introduced, a generative framework on the Wasserstein space of a Riemannian manifold that can generate whole single-cell samples in hyperspherical latent spaces and protein conformational ensembles on the torus by respecting the intrinsic geometry of the data.
Abstract
Many scientific datasets, such as molecular conformational ensembles or single-cell tissue measurements, are naturally modeled as meta-distributions: distributions over probability measures on non-Euclidean domains. Existing generative methods largely assume Euclidean geometry and fail to capture this structure. We introduce Riemannian Wasserstein Entropic Flow Matching (RWEFM), a generative framework on the Wasserstein space $\mathcal{P}_2(\mathcal{M})$ of a Riemannian manifold $(\mathcal{M},g)$. RWEFM is trained by regressing a neural vector field onto Riemannian optimal transport velocities, using McCann displacement interpolations as conditional paths. We confirm theoretically that this construction leads to a valid flow matching approach on $\mathcal{P}_2(\mathcal{M})$ and introduce the Riemannian Entropic Map, a GPU-efficient approximation of the optimal transport map on manifolds. Our experiments show that by respecting the intrinsic geometry of the data, RWEFM can generate whole single-cell samples in hyperspherical latent spaces and protein conformational ensembles on the torus. As RWEFM requires only a geodesic distance and a projection operator, it is not restricted to manifolds with closed-form geometry, which we demonstrate by generating distributions on a general triangulated mesh.
Entropic Optimal Transport (EOT) has become a practical framework for learning stochastic couplings between complex distributions, with applications in generative modeling and domain adaptation. However, most EOT solvers are designed for Euclidean spaces, while manifold extensions remain limited and often rely on costl...
Xavier Aramayo-Carrasco, Petr Mokrov, Alexander Korotin· 0 citations
Manifold-valued data, and consequently the distributions they induce, are prevalent across many domains, ranging from the locations of geospatial events, such as earthquakes, to biomolecular torsion angles that encode information about three-dimensional structure. While diffusion and flow-based generative models have b...
Ualibyek Nurgulan, Seungwoo Yoo, Prin Phunyaphibarn et al.· 0 citations
This work develops a general framework that separates score discretization from Brownian-motion simulation and allows multiple geodesic random-walk steps per score evaluation and provides a sharper characterization of the convergence and sampling complexity of Riemannian diffusion models.
The results demonstrate that flow matching naturally adapts to the intrinsic geometry of data and mitigates the curse of dimensionality, as the convergence exponent depends on the intrinsic rather than ambient dimension.
Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett· 7 citations· ⚡1
By framing hyperbolic manifolds as quadric level sets, MAN resolves hyperbolic geometry by combining linear Lorentz group transport with non-linear cone lifting and closed-form radial rescaling, evaluating in a single forward pass without numerical ODE solvers or iterative retractions.
This work introduces the class $\mathcal{P}_\psi(\mu)$ of measures that differ from a reference measure only through a finite-dimensional map $\psi$ while preserving the reference conditionals on its fibers, and develops approximation theory for fitting within it.
R. Baptista, Bamdad Hosseini, Alexander Hsu· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026