Stable probabilistic emulation of partially observed dynamical systems
cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale
- ACE: A fast, skillful learned global atmospheric model for climate prediction
- ACE2: Accurately learning subseasonal to decadal atmospheric variability and forced responses
- LUCIE: A Lightweight Uncoupled ClImate Emulator with long-term stability and physical consistency for O(1000)-member ensembles
- LUCIE-3D: A three-dimensional climate emulator for forced responses
- SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulators
- Score-Based Modeling of Effective Langevin Dynamics with State-Dependent Mobility
- Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation
- Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos
- Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems
- Learned Coarse Models for Efficient Turbulence Simulation
- Forecasting Global Weather with Graph Neural Networks
- Challenges of learning multi-scale dynamics with AI weather models: Implications for stability and one solution
- Physics constraints and response validation in discrete-time reduced-order modeling: from idealized turbulent systems to climate dynamics
- Flow Matching for Generative Modeling
- Wavelet Flow Matching for Multi-Scale Physics Emulation
- On Forgetting and Stability of Score-based Generative models
- Deep Generative Spatiotemporal Engression for Probabilistic Forecasting of Epidemics
- Let the Dynamics Flow: Stable Flow Matching Dynamical Systems
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