Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
arXiv preprint arXiv:2208.14699 , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
verdicts
UNVERDICTED 8representative citing papers
ABC enables any-subset autoregressive generation of continuous stochastic processes via non-Markovian diffusion bridges that track physical time and allow path-dependent conditioning.
Stochastic interpolants unify flow-based and diffusion-based generative models by bridging target densities exactly via latent-variable processes whose drifts minimize quadratic objectives.
Presents adjoint matching for scalable max-ent RL training of diffusion policies, enabling simulation-free optimization.
Recasting diffusion noise schedule design as optimal control on Fisher information yields sufficient conditions for O(d/n) sampling error and parametric closed-form schedules that generalize exponential/sigmoid ones and improve empirical performance.
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
Rectified Schrödinger Bridge Matching uses ε-invariant velocity structure and a learned prior so generative navigation policies reach ~94% cosine similarity and 92% success in three integration steps without distillation.
Notes recapitulating high-level principles of generative modeling and showing connections between optimal transport, Schrödinger bridge, and flow matching.
citing papers explorer
-
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
-
ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space
ABC enables any-subset autoregressive generation of continuous stochastic processes via non-Markovian diffusion bridges that track physical time and allow path-dependent conditioning.
-
Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
Stochastic interpolants unify flow-based and diffusion-based generative models by bridging target densities exactly via latent-variable processes whose drifts minimize quadratic objectives.
-
Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching
Presents adjoint matching for scalable max-ent RL training of diffusion policies, enabling simulation-free optimization.
-
Noise Schedule Design for Diffusion Models: An Optimal Control Perspective
Recasting diffusion noise schedule design as optimal control on Fisher information yields sufficient conditions for O(d/n) sampling error and parametric closed-form schedules that generalize exponential/sigmoid ones and improve empirical performance.
-
Rectified Flow: A Marginal Preserving Approach to Optimal Transport
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
-
Rectified Schr\"odinger Bridge Matching for Few-Step Visual Navigation
Rectified Schrödinger Bridge Matching uses ε-invariant velocity structure and a learned prior so generative navigation policies reach ~94% cosine similarity and 92% success in three integration steps without distillation.
-
Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{\"o}dinger bridge
Notes recapitulating high-level principles of generative modeling and showing connections between optimal transport, Schrödinger bridge, and flow matching.