An analytic uniform ergodic latent trajectory is pushed forward by a conditional flow matching map to produce asymptotically ergodic trajectories matching any target density with provable coverage bounds.
arXiv preprint arXiv:2404.00551 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Sharp Lipschitz regularity for flow-matching vector fields and diffusion scores, with optimal time/dimension dependence, gives √d/N Wasserstein discretization error for Euler samplers and globally Lipschitz Gaussian-to-target transport maps implying Poincaré and log-Sobolev inequalities.
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
RepFlow combines representation learning and conditional flow matching to estimate both point and distributional causal effects while mitigating selection bias via entropically regularized Wasserstein distance on normalized latent representations.
citing papers explorer
-
Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow Matching
An analytic uniform ergodic latent trajectory is pushed forward by a conditional flow matching map to produce asymptotically ergodic trajectories matching any target density with provable coverage bounds.
-
Lipschitz regularity in Flow Matching and Diffusion Models: sharp sampling rates and functional inequalities
Sharp Lipschitz regularity for flow-matching vector fields and diffusion scores, with optimal time/dimension dependence, gives √d/N Wasserstein discretization error for Euler samplers and globally Lipschitz Gaussian-to-target transport maps implying Poincaré and log-Sobolev inequalities.
-
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
dFlowGRPO is a new rate-aware RL method for discrete flow models that outperforms prior GRPO approaches on image generation and matches continuous flow models while supporting broad probability paths.
-
RepFlow: Representation Enhanced Flow Matching for Causal Effect Estimation
RepFlow combines representation learning and conditional flow matching to estimate both point and distributional causal effects while mitigating selection bias via entropically regularized Wasserstein distance on normalized latent representations.