Constraint-Aware Flow Matching integrates constraint projections into the flow matching training objective to align model dynamics with constrained sampling and reduce distributional shift.
hub
arXiv preprint arXiv:2307.08698 , year=
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A geometric latent-subspace model on Riemannian manifolds of categorical distributions enables low-dimensional generative modeling of discrete data via isometries and geometric PCA for flow matching.
Image autoregressive models leak substantially more training data than diffusion models under membership inference, dataset inference with as few as 4 samples, and data extraction attacks.
A feature supervision approach using SigLIP 2 extracts multi-granularity vision-aligned text representations to supervise MM-DiT image branches, pushing the Pareto frontier for portrait generation across alignment, realism, and aesthetics.
BeyondDrive augments imitation learning with synthesized safety-critical negative trajectories and a repulsive loss to improve safety in autonomous driving, reporting 89.7 PDMS on NAVSIMv1 and generalization to other models.
Wavelet Flow Matching emulates multi-scale PDE-governed systems by transporting velocities directly in a hierarchical wavelet representation via U-Net, yielding improved long-horizon stability and spectral accuracy on fluid benchmarks.
An optimal control formulation adds time-dependent perturbations to the reverse diffusion process to match target attribute distributions while preserving sample fidelity.
AuxPath-FM extends flow matching to arbitrary auxiliary distributions while preserving the continuity equation and marginal training objective.
P-Guide achieves single-pass classifier-free guidance in flow matching by modulating the initial latent state and is equivalent to standard CFG under a first-order approximation while cutting latency by half.
Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.
BLAE adds injective regularization via a separation criterion and bi-Lipschitz constraints to guarantee injectivity and geometric preservation in autoencoders, outperforming prior methods on manifold fidelity under sparsity and distribution shifts.
VicoEdit performs training-free image editing by transforming source images directly with visual context and concept-alignment-guided posterior sampling, outperforming training-based methods.
MPDiT uses a hierarchical multi-patch design in transformers to lower computation in diffusion models by handling coarse global features first then fine local details, plus faster-converging embeddings.
Contrast-X benchmark and FlowMI model enable synthesis of contrast-enhanced images from arbitrary non-contrast modality inputs using multi-modal flow matching.
Latent Stochastic Interpolants jointly optimize encoder-decoder and a latent-space stochastic interpolant using a continuous-time ELBO to transform arbitrary priors into aggregated posteriors.
EventFlow applies flow matching to learn joint distributions over event times for temporal point processes, reporting 20-53% lower forecast error than autoregressive baselines on standard TPP benchmarks with fewer sampling calls.
Stronger physics priors in neural networks for spatio-temporal shear flow forecasting yield substantially lower training carbon footprints than weak or no priors, though inference savings are less consistent.
citing papers explorer
-
Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling
Constraint-Aware Flow Matching integrates constraint projections into the flow matching training objective to align model dynamics with constrained sampling and reduce distributional shift.
-
Generative Modeling of Discrete Data Using Geometric Latent Subspaces
A geometric latent-subspace model on Riemannian manifolds of categorical distributions enables low-dimensional generative modeling of discrete data via isometries and geometric PCA for flow matching.
-
Privacy Attacks on Image AutoRegressive Models
Image autoregressive models leak substantially more training data than diffusion models under membership inference, dataset inference with as few as 4 samples, and data extraction attacks.
-
Pareto-Enhanced Portrait Generation: Vision-Aligned Text Supervision for Alignment, Realism, and Aesthetics
A feature supervision approach using SigLIP 2 extracts multi-granularity vision-aligned text representations to supervise MM-DiT image branches, pushing the Pareto frontier for portrait generation across alignment, realism, and aesthetics.
-
Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
BeyondDrive augments imitation learning with synthesized safety-critical negative trajectories and a repulsive loss to improve safety in autonomous driving, reporting 89.7 PDMS on NAVSIMv1 and generalization to other models.
-
Wavelet Flow Matching for Multi-Scale Physics Emulation
Wavelet Flow Matching emulates multi-scale PDE-governed systems by transporting velocities directly in a hierarchical wavelet representation via U-Net, yielding improved long-horizon stability and spectral accuracy on fluid benchmarks.
-
Inference-Time Attribute Distribution Alignment for Unconditional Diffusion
An optimal control formulation adds time-dependent perturbations to the reverse diffusion process to match target attribute distributions while preserving sample fidelity.
-
Flow Matching with Arbitrary Auxiliary Paths
AuxPath-FM extends flow matching to arbitrary auxiliary distributions while preserving the continuity equation and marginal training objective.
-
P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference
P-Guide achieves single-pass classifier-free guidance in flow matching by modulating the initial latent state and is equivalent to standard CFG under a first-order approximation while cutting latency by half.
-
A Few-Step Generative Model on Cumulative Flow Maps
Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.
-
Bi-Lipschitz Autoencoder With Injectivity Guarantee
BLAE adds injective regularization via a separation criterion and bi-Lipschitz constraints to guarantee injectivity and geometric preservation in autoencoders, outperforming prior methods on manifold fidelity under sparsity and distribution shifts.
-
Training-Free Image Editing with Visual Context Integration and Concept Alignment
VicoEdit performs training-free image editing by transforming source images directly with visual context and concept-alignment-guided posterior sampling, outperforming training-based methods.
-
MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
MPDiT uses a hierarchical multi-patch design in transformers to lower computation in diffusion models by handling coarse global features first then fine local details, plus faster-converging embeddings.
-
Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching
Contrast-X benchmark and FlowMI model enable synthesis of contrast-enhanced images from arbitrary non-contrast modality inputs using multi-modal flow matching.
-
Latent Stochastic Interpolants
Latent Stochastic Interpolants jointly optimize encoder-decoder and a latent-space stochastic interpolant using a continuous-time ELBO to transform arbitrary priors into aggregated posteriors.
-
EventFlow: Forecasting Temporal Point Processes with Flow Matching
EventFlow applies flow matching to learn joint distributions over event times for temporal point processes, reporting 20-53% lower forecast error than autoregressive baselines on standard TPP benchmarks with fewer sampling calls.
-
Physics Priors Offer Useful Accuracy-Carbon Trade-Offs in Spatio-Temporal Forecasting
Stronger physics priors in neural networks for spatio-temporal shear flow forecasting yield substantially lower training carbon footprints than weak or no priors, though inference savings are less consistent.