Introduces a marginal-alignment regularizer for reflow distillation of diffusion models that aligns endpoint marginals, supported by a telescoping TV bound and benchmark experiments.
Flow straight and fast: Learning to generate and transfer data with rectified flow
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
background 1polarities
background 1representative citing papers
Derives a conditional-marginal entropy-rate objective for bridge-aware discretization that yields U-shaped schedules and improves low-NFE sample quality on 2D, CIFAR-10, and protein tasks.
AGMs use a lightweight learned potential V_phi with stop-gradient to selectively weight informative bridge samples in generative model training, yielding better fidelity and coverage.
CCVFM uses an entropic Sinkhorn coreset to induce a closed-form Gaussian mixture source for hierarchical rectified flow matching, then trains a lightweight correction flow on the residual, achieving competitive few-step image generation.
Projecting VAE latents to a fixed spherical radius and replacing linear interpolation with spherical linear interpolation improves class-conditional ImageNet-256 FID while leaving the diffusion architecture unchanged.
PVRF combines zero-shot VLM-based weather perception with perception-adaptive rectified flow refinement to achieve all-in-one adverse weather removal with improved fidelity and cross-dataset generalization.
PRISM iteratively transforms semantic priors into behavior-conditioned posteriors via cross-modal refinement to improve representation learning on dynamic text-attributed graphs.
Venom is an educational PyTorch toolkit that packages multiple generative modeling families under a single MNIST-first interface with reproducible scripts and tutorials.
citing papers explorer
-
Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
Introduces a marginal-alignment regularizer for reflow distillation of diffusion models that aligns endpoint marginals, supported by a telescoping TV bound and benchmark experiments.
-
Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr\"odinger Samplers
Derives a conditional-marginal entropy-rate objective for bridge-aware discretization that yields U-shaped schedules and improves low-NFE sample quality on 2D, CIFAR-10, and protein tasks.
-
Action-Inspired Generative Models
AGMs use a lightweight learned potential V_phi with stop-gradient to selectively weight informative bridge samples in generative model training, yielding better fidelity and coverage.
-
Coreset-Induced Conditional Velocity Flow Matching
CCVFM uses an entropic Sinkhorn coreset to induce a closed-form Gaussian mixture source for hierarchical rectified flow matching, then trains a lightweight correction flow on the residual, achieving competitive few-step image generation.
-
Aligning Latent Geometry for Spherical Flow Matching in Image Generation
Projecting VAE latents to a fixed spherical radius and replacing linear interpolation with spherical linear interpolation improves class-conditional ImageNet-256 FID while leaving the diffusion architecture unchanged.
-
PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
PVRF combines zero-shot VLM-based weather perception with perception-adaptive rectified flow refinement to achieve all-in-one adverse weather removal with improved fidelity and cross-dataset generalization.
-
PRISM: Iterative Cross-Modal Posterior Refinement for Dynamic Text-Attributed Graphs
PRISM iteratively transforms semantic priors into behavior-conditioned posteriors via cross-modal refinement to improve representation learning on dynamic text-attributed graphs.
-
Venom: A PyTorch Generative Modeling Toolkit
Venom is an educational PyTorch toolkit that packages multiple generative modeling families under a single MNIST-first interface with reproducible scripts and tutorials.