Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting
cs.LG
Submitted: 2026-05-07
Updated: 2026-11-06
Code: https://github.com/Sunxkissed/Tyche
Terminology
Sources
- Skillful joint probabilistic weather forecasting from marginals
- Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics
- ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting
- One Step Diffusion via Shortcut Models
- OneForecast: A Universal Framework for Global and Regional Weather Forecasting
- Mean Flows for One-step Generative Modeling
- Improved Mean Flows: On the Challenges of Fastforward Generative Models
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models
- FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
- GLU Variants Improve Transformer
- Consistency Models
- Swift: An Autoregressive Consistency Model for Efficient Weather Forecasting
- GEN2: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes
- Advanced Long-term Earth System Forecasting
- AlphaFlow: Understanding and Improving MeanFlow Models
- LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis