A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
International conference on machine learning , pages=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
A recursive cubing framework identifies stable hyperparameter regions for MC dropout uncertainty quantification in spatial deep learning and produces competitive or superior predictive intervals versus a statistical baseline on simulations and land-surface temperature data.
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.
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.
Bayesian inverse problem with diffusion model priors for CML-based rain field reconstruction outperforms baselines by preserving rainfall statistics better than Gaussian processes.
citing papers explorer
-
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.
-
A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning
A recursive cubing framework identifies stable hyperparameter regions for MC dropout uncertainty quantification in spatial deep learning and produces competitive or superior predictive intervals versus a statistical baseline on simulations and land-surface temperature data.
-
Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.
-
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.
-
Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors
Bayesian inverse problem with diffusion model priors for CML-based rain field reconstruction outperforms baselines by preserving rainfall statistics better than Gaussian processes.