RW-Flow presents a new one‑step generative framework for data on compact manifolds, leveraging Wasserstein gradient flows. The authors derive a necessary and sufficient identifiability condition for velocity fields on compact, connected Riemannian manifolds, showing that a symmetric, Lipschitz‑continuous cost function yields identifiability iff its Gibbs kernel is nondegenerate. Experiments on geospatial events, protein and RNA torsion angles, and discretized manifolds demonstrate that RW‑Flow surpasses existing one‑step methods across most benchmark settings.
By Ualibyek Nurgulan, Seungwoo Yoo, Prin Phunyaphibarn, Minhyuk Sung
arXiv:2610. 02663v1 Announce Type: cross Abstract: Despite the remarkable empirical success of flow-matching models, their statistical generalization guarantees remain underdeveloped.
By Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett
arXiv:2511. 17812v3 Announce Type: replace-cross Abstract: Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challenging under limited sampling budgets.
By Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei, Truong Nguyen
arXiv:2609.25659v1 Announce Type: new
Abstract: Many scientific datasets, such as molecular conformational ensembles or single-cell tissue measurements, are naturally modeled as meta-distributions: d...
By Doron Haviv, Edward De Brouwer, Rishabh Anand, Rex Ying, A\"icha Bentaieb, Gabriele Scalia, Hector Corrada Bravo
ReSFlow is a generative model that learns geodesic trajectories on statistical manifolds to enable one‑step categorical generation. By rectifying continuous‑time flows to follow intrinsic Riemannian geometry, it reduces transport cost and eliminates the need for multi‑step numerical integration. Experiments across image, text, and biological datasets show that ReSFlow achieves superior one‑step generation quality compared to prior methods.
By Xiaohuan Jia, Renzhe Xu, Xiao Wang, Jiayun Wu, Shaohua Fan
The paper investigates when conditional flow matching (CFM) can replace pointwise negative log-likelihood (NLL) calculations. It shows that for linear Gaussian paths, the endpoint NLL can be exactly decomposed into entropy, a weighted CFM objective, and residual terms, meaning CFM-only estimates are exact only when these residuals cancel. The study finds that ordinary CFM is generally not a pointwise NLL estimator, and even weighted variants may not fully eliminate bias, especially in training or on‑policy settings, with experiments confirming these theoretical insights.
By Yansen Han, Hongxin Sun, Tao Lin