Heavy-tailed diffusion models

K Pandey, J Pathak, Y Xu, S Mandt, M Pritchard… - arxiv preprint arxiv …, 2024 - arxiv.org
Diffusion models achieve state-of-the-art generation quality across many applications, but
their ability to capture rare or extreme events in heavy-tailed distributions remains unclear. In …

A generative diffusion model for probabilistic ensembles of precipitation maps conditioned on multisensor satellite observations

C Guilloteau, G Kerrigan, K Nelson, G Migliorini… - arxiv preprint arxiv …, 2024 - arxiv.org
A generative diffusion model is used to produce probabilistic ensembles of precipitation
intensity maps at the 1-hour 5-km resolution. The generation is conditioned on infrared and …

Kolmogorov Arnold Neural Interpolator for Downscaling and Correcting Meteorological Fields from In-Situ Observations

Z Liu, H Chen, L Bai, W Li, Z Zou, Z Shi - arxiv preprint arxiv:2501.14404, 2025 - arxiv.org
Obtaining accurate weather forecasts at station locations is a critical challenge due to
systematic biases arising from the mismatch between multi-scale, continuous atmospheric …