Riemannian Flow Matching

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 24

All topics

Manifold-Stable Flow Matching
Sep 28, 2026Amirhossein Nazerian, Ali Pezeshki, Jianguo ZhaoRiemannian Flow Matching Conditional Velocity
Department of Mechanical Engineering Colorado State University Fort Collins, CO 80523, USA · Department of Electrical and Computer Engineering Colorado State University Fort Collins, CO 80523, USA
Probabilistic Geodesic Flow Matching on Location-Scale Families
Sep 28, 2026Zeyuan Yu, Zhi Chang, Shiwei LanRiemannian Flow Matching Discriminative Congruence Transform
School of Mathematical & Statistical Sciences Arizona State University Tempe, AZ 85287 USA
Naturalness-guided Manifold Flow Matching for Sign Language Production
Sep 27, 2026Jiayi He, Shengeng Tang, Sisi You +3Sign Language Translation Riemannian Flow Matching
Hefei University of Technology
When Riemann flows with Wasserstein: Generative Modeling of Probability Distributions on Manifolds
Sep 22, 2026Doron Haviv, Edward De Brouwer, Rishabh Anand +4Riemannian Flow Matching Data Manifold
Genentech Inc., South San Francisco, CA. · Yale University, New Haven, CT.
Escaping the Euclidean Void: Manifold-Informed Flow Matching for Sequential Recommendation
Jul 26, 2026Dengzhao Fang, Jingtong Gao, Yu Li +2Sequential Recommendation Riemannian Flow Matching
Jilin University · City University of Hong Kong
Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
Jul 21, 2026Lisa Weijler, Irene Ballester, Guofeng Mei +23D Foundation Models Riemannian Flow Matching
TU Wien · Fondazione Bruno Kessler · Imperial College London
Learning Standard Model structure from LHC data with Riemannian flow matching
Jul 17, 2026Midori Kato, Kevin A. Urquía-Calderón, Inar Timiryasov +1Riemannian Flow Matching Generative Pretrained Transformers
Niels Bohr Institute, University of Copenhagen, Jagtvej 155A, DK-2200, Copenhagen, Denmark
FlowPET: Physics-Informed Symplectic Flow Matching for Low-Count PET Reconstruction
Jul 13, 2026Zheng Zhang, Hao Tang, Yingying Hu +2Positron Emission Tomography Riemannian Flow Matching
Centre for Smart Health, The Hong Kong Polytechnic University, Hong Kong, China · Department of Nuclear Medicine, Sun Yat-sen University Cancer Center, Guangzhou, China · Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation
Jun 25, 2026Chunshi Wang, Haohan Weng, Junliang Ye +9Mesh Generation Riemannian Flow Matching
1ZJU · 2Tencent · 3THU +3
The Geometry Behind Diffusion and Flow Matching: Gradient Flows and Geodesics in Wasserstein Space
Jun 23, 2026Yian Yao, Weiwei ZhangRiemannian Flow Matching Wasserstein Gradient Flows
from the mortal world · from heaven
MeshFlow: Mesh Generation with Equivariant Flow Matching
Jun 22, 2026Qi Sun, Kiyohiro Nakayama, Jing Nathan Yan +6Mesh Generation Riemannian Flow Matching
City University of Hong Kong, Hong Kong · Stanford University, USA · Cornell Tech, USA +1
Topological Flow Matching
Jun 14, 2026Kacper Wyrwal, İsmail İlkan Ceylan, Alexander TongRiemannian Flow Matching Topology
University of Oxford · TU Wien · AITHYRA
Riemannian Metric Matching for Scalable Geometric Modeling of Distributions
Jun 12, 2026Jacob Bamberger, Adam Gosztolai, Pierre Vandergheynst +2Riemannian Manifolds Riemannian Flow Matching
Department of Computer Science, University of Oxford, Oxford, UK · Institute of Artificial Intelligence, Medical University of Vienna, Vienna, Austria · EPFL, Lausanne, Switzerland +1
STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation
Jun 5, 2026Won June Cho, Daeky Jeong, Hyeongyeol Lim +1Diffusion Transformers Riemannian Flow Matching
DEEPNOID Inc.
Geodesic Flow Matching on a Riemannian Degradation Manifold for Blind Image Restoration
Jun 4, 2026Akshay Janardan Bankar, Ankita Chatterjee, Sayan Banerjee +3Riemannian Flow Matching Image Restoration
Samsung Research Institute, Bangalore, India
Geodesic Flow Matching for Denoising High-Dimensional Structured Representations
May 29, 2026Karim Habashy, Chris EliasmithRiemannian Flow Matching Semantic Geometry
Department of Systems Design Engineering, University of Waterloo, Waterloo, Canada · Center For Theoretical Neuroscience, University of Waterloo, Waterloo, Canada · Department of Philosophy, University of Waterloo, Waterloo, Canada
Geometric Flow Matching for Molecular Conformation Generation via Manifold Decomposition
May 25, 2026Yunqing Liu, Yi Zhou, Wenqi FanConformational Ensembles Riemannian Flow Matching
The Hong Kong Polytechnic University Hong Kong, China
GeoFlowVLM: Geometry-Aware Joint Uncertainty for Frozen Vision-Language Embedding
May 13, 2026Mayank Nautiyal, Li Ju, Andreas Hellander +2Recent Vision-Language Models Frozen Vision-Language Models
Department of Information Technology, Uppsala University, Uppsala, Sweden · SciLifeLab, Uppsala University, Uppsala, Sweden
MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching
May 8, 2026Salim Khazem, Ibrahim Mohamed Serouis, Zakaria EzzahedFew-Shot Learning Frozen Backbone
Talan Research Center, Paris, France
Tessellations of Semi-Discrete Flow Matching
May 8, 2026Emile Pierret, Johannes Hertrich, Samuel Hurault +1Riemannian Flow Matching Conditional Flow Matching
DMA, ENS-PSL, MAP5 · DMA, ENS-PSL · LIGM, Univ. Gustave Eiffel, CNRS
Flow Matching on Symmetric Spaces
May 5, 2026Francesco Ruscelli, Ferdinando Zanchetta, Rita FioresiRiemannian Flow Matching Riemannian Manifolds
Institute for Mathematics University of Heidelberg 69120 Heidelberg, Germany · Department of Pharmacy and Biotechnologies University of Bologna Bologna, Italy
Complex normalizing flows can almost be information Kähler-Ricci flows
Apr 20, 2026Andrew GracykNormalizing Flows Riemannian Flow Matching
Department of Mathematics, Purdue University, West Lafayette, IN 47907, United States
Convergence Rates for Distribution Matching with Sliced Optimal Transport
Feb 11, 2026Gauthier Thurin, Claire Boyer, Kimia NadjahiOptimal Transport Approach Wasserstein Distance
ENS-PSL · CNRS, ENS Paris, France · LMO, IUF, CELESTE +2
Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
Feb 10, 2026Amandeep Kumar, Vishal M. PatelDiffusion Transformers Riemannian Flow Matching
Johns Hopkins University

Sep 28, 2026, cs.LGJ/K move · Enter open · S save

Manifold-Stable Flow Matching

Amirhossein Nazerian, Ali Pezeshki, Jianguo Zhao

Department of Mechanical Engineering Colorado State University Fort Collins, CO 80523, USA · Department of Electrical and Computer Engineering Colorado State University Fort Collins, CO 80523, USA

Riemannian Flow Matching Conditional Velocity

Open paper AskPDF arXiv

Flow matching (FM) learns generative dynamics through velocity regression. Geometric FM variants commonly assume a prior supported on the data manifold, requiring geometric knowledge that is often unavailable. Without such knowledge, low regression error alone does not guarantee manifold adherence. Adherence keeps generated samples within valid configurations and is empirically associated with better task performance. We introduce manifold-stable flow matching (MSFM), which can start from an arbitrary ambient prior, not necessarily supported on the manifold. Using tools from nonlinear dynamics, namely contraction theory, MSFM combines learned tangential transport with prescribed normal contraction. The construction uses analytical projectors for known manifolds and local affine proxies estimated by principal component analysis for unknown data geometry. By implementing contraction theory in both cases of known and unknown manifolds, we guarantee manifold invariance and transverse convergence to the manifold within a desired time window (e.g., one second). We derive a family of compatible probability paths and decompose the training loss into a learnable tangential term and a normal residual. An ellipse experiment attains a mean terminal off-manifold error of order

10^{-6}

. In Push-T robotic experiments, MSFM raises success from

74\%

82\%

. In the Robomimic Square task, success increases from

60\%

72\%

, while rotation-manifold deviation decreases from order

10^{-2}

10^{-7}

. The MSFM terminal geometric errors are controlled by the chosen numerical tolerance. These results demonstrate stronger geometric adherence and higher observed task performance, supporting prescribed normal contraction as a complement to learned generative transport.

Momentum

Related topics

Latest papers 24