Scale-Recursive Rectified Flows for Few-Step Precipitation Ensembles

arXiv:2610.02611 · cs.LG, cs.CV · Submitted 2026-10-02 · Read on arXiv

cs.LG, cs.CV

Submitted: 2026-10-02

Updated: 2026-10-02

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Rectified Flow — 1× in this paper · explained in 3 episodes

Sources

• Scale-Adaptive Generative Flows for Multiscale Scientific Data
• Neural Stochastic Processes for Satellite Precipitation Refinement
• Multi-scale Generative Modeling for Fast Sampling
• Colored Noise Diffusion Sampling

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks