One-Step Generation via Riemannian Wasserstein Gradient Flows

arXiv:2610.04454 · cs.LG · Submitted 2026-10-03 · Read on arXiv

cs.LG

Submitted: 2026-10-03

Updated: 2026-10-03

Terminology

• Gradient Flow — 1× in this paper · explained in 2 episodes

Sources

• Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergences
• One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling
• Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds
• Generative Modeling via Drifting
• Kernel-Gradient Drifting Models
• Drifting Fields are not Conservative
• On the Wasserstein Gradient Flow Interpretation of Drifting Models
• One-Step Generative Modeling via Wasserstein Gradient Flows
• Sinkhorn-Drifting Generative Models
• A Unified View of Score-Based and Drifting Models
• Flow Map Language Models: One-step Language Modeling via Continuous Denoising
• Drifting Objectives for Refining Discrete Diffusion Language Models
• Coupling Models for One-Step Discrete Generation
• Discrete Flow Maps
• Dirichlet Flow Matching with Applications to DNA Sequence Design
• Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective
• Riemannian MeanFlow

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks