mlsanityData to 14 Oct 2026

Swift: An Autoregressive Consistency Model for Efficient Weather Forecasting

arXiv 2509.25631 ↗First posted 30 Sep 2025cs.LGcited by 13

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Diffusion models offer a physically grounded framework for probabilistic weather forecasting, but their typical reliance on slow, iterative solvers during inference makes them impractical for subseasonal-to-seasonal (S2S) applications where long lead-times and domain-driven calibration are essential. To address this, we introduce Swift, a single-step consistency model that, for the first time, enables autoregressive finetuning of a probability flow model with a continuous ranked probability score (CRPS) objective. This eliminates the need for multi-model ensembling or parameter perturbations. Results show that Swift produces skillful 6-hourly forecasts that remain stable for up to 75 days, running 39× faster than state-of-the-art diffusion baselines while achieving forecast skill competitive with the numerical-based, operational IFS ENS. This marks a step toward efficient and reliable ensemble forecasting from medium-range to seasonal-scales.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 30 of its 46 references that are in the map. First posted on arXiv 30 Sep 2025.

Builds on

30 of 46 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions16 Sep
  2. 2024ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting17 Dec
  3. 2024DiffObs: Generative Diffusion for Global Forecasting of Satellite Observations4 Apr
  4. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling24 Sep
  5. 2023Improving and generalizing flow-based generative models with minibatch optimal transport1 Feb
  6. 2022Flow Matching for Generative Modeling6 Oct
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 23

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2022Classifier-Free Diffusion Guidancecited by 5,847
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  6. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  7. 2023Consistency Modelscited by 1,822
  8. 2020GLU Variants Improve Transformercited by 1,804
  9. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  10. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  11. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  12. 2016Training Deep Nets with Sublinear Memory Costcited by 848
11 more
  1. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
  2. 2023Improved Techniques for Training Consistency Modelscited by 439
  3. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 283
  4. 2023Neural General Circulation Models for Weather and Climatecited by 239
  5. 2023WeatherBench 2: A benchmark for the next generation of data-driven global weather modelscited by 236
  6. 2023GenCast: Diffusion-based ensemble forecasting for medium-range weathercited by 177
  7. 2022Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecastcited by 166
  8. 2023Scaling transformer neural networks for skillful and reliable medium-range weather forecastingcited by 110
  9. 2025Skillful joint probabilistic weather forecasting from marginalscited by 63
  10. 2023Challenges of learning multi-scale dynamics with AI weather models: Implications for stability and one solutioncited by 31
  11. 2024Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Predictioncited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 13.

13 papers.

Sort:

By area:

  1. 2026Demystifying Data-Driven Probabilistic Medium-Range Weather Forecastingcited by 15
  2. 2026U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecastercited by 12
  3. 2026Probabilistic Retrofitting of Learned Simulatorscited by 7
  4. 2026Tyche: One Step Flow for Efficient Probabilistic Weather Forecastingcited by 3
  5. 2026Probabilistic Transformers for Joint Modeling of Global Weather Dynamics and Decision-Centric Variablescited by 1
  6. 2026Super-Resolving Coarse-Resolution Weather Forecasts With Flow Matchingcited by 1
  7. 2026Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Trainingcited by 0
  8. 2026Dual-Scale Temporal Fusion Reveals Structured Predictability in Subseasonal-to-Seasonal Temperature Predictioncited by 0
  9. 2026Emulating the Forced Response of Climate Models with Generative Machine Learningcited by 0
  10. 2026Timestep-Conditioned Transformers for Global Weather Forecastingcited by 0
  11. 2026Diffusion Distillation for Efficient Weather Ensemblescited by 0
  12. 2026Every Fixed Metric Has a Blind Spot: A Learned Atmospheric Critic for Scoring Forecast Realismcited by 0
1 more
  1. 2026Proper Scoring Rule-based Diffusion for Probabilistic Weather Forecastingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Continuous Ensemble Weather Forecasting with Diffusion models
  2. 2025Data-Efficient Ensemble Weather Forecasting with Diffusion Models
  3. 2025LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting
  4. 2025DEF: Diffusion-augmented Ensemble Forecasting
  5. 2026Universal Diffusion-Based Probabilistic Downscaling
  6. 2024CoDiCast: Conditional Diffusion Model for Global Weather Prediction with Uncertainty Quantification
  7. 2023SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Models
  8. 2026PuYun-LDM: A Latent Diffusion Model for High-Resolution Ensemble Weather Forecasts