arXiv Computer Vision
A Lagrangian View of Flow Matching
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
Aug 31
A Lagrangian View of Flow Matching
Modern explicit-time generative models, such as Flow Matching [Lipman et al., 2023] and Rectified Flow [Liu et al., 2023], are typically derived top-down via Optimal Transport and the continuity equat...
arXiv Machine Learning
Aug 10
Limit Points of Reflow with Minibatch Optimal Transport
arXiv:2608. 07042v1 Announce Type: cross Abstract: Rectified flows, also called flow matching or stochastic interpolants, are generative models that learn a time-dependent vector field steering a probability curve between two probability distributions, usually referred to as latent and target distributions.
Hugging Face Trending Papers
Jul 5
Constrained Flow Matching via Lagrangian Dual Flows
Flow matching is a powerful tool for generative modeling, but emerging applications in robotics, planning, and physics require inference-time constraints on generated outputs. Such constraints are often complex and highly nonlinear.
arXiv Machine Learning
Jun 3
A Quantitative Approximation Framework for Flow Distillation in Diffusion Models
arXiv:2606. 03820v1 Announce Type: cross Abstract: We develop a quantitative approximation framework for diffusion distillation, viewing few-step sampling as error propagation under compositions of learned flow maps.
arXiv Machine Learning
Aug 4
Beckmann Transport Models: From Autonomous Flows to One-Step Maps
arXiv:2608. 01692v1 Announce Type: new Abstract: We propose an instantiation of flow matching that relies on a time-independent velocity field (an \emph{autonomous flow}) to exactly map between two distributions, so long as the target is singular, i.
arXiv Machine Learning
Jul 7
Constrained Flow Matching via Lagrangian Dual Flows
arXiv:2607. 04513v1 Announce Type: cross Abstract: Flow matching is a powerful tool for generative modeling, but emerging applications in robotics, planning, and physics require inference-time constraints on generated outputs.