Staying on the Attractor: Supervising Neural Surrogates of 3D Turbulence Where They Leave It
cs.LG, physics.flu-dyn
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- Memory-Conditioned Flow-Matching for Stable Autoregressive PDE Rollouts
- FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale
- When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
- Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training
- Improved deep learning of chaotic dynamical systems with multistep penalty losses
- PEST: Physics-Enhanced Swin Transformer for 3D Turbulence Simulation
- TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning
- FlowRefiner: Flow Matching-Based Iterative Refinement for 3D Turbulent Flow Simulation
- Physics-Preserving Latent Compression for Zero-Shot Resolution Transfer in 3D Turbulence
- Predictivity and Utility of Neural Surrogates of Multiscale PDEs
- Inverse Evolution Data Augmentation for Neural PDE Solvers
- Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Towards Stability of Autoregressive Neural Operators
- Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence
- Jacobian-Adaptive Weighting for Stability: Enhancing Long-term Rollout of Neural Partial Differential Equation Solvers via Spatially-Adaptive Regularization
- Stable Fine-Time-Step Long-Horizon Turbulence Prediction with a Multi-Stepsize Mixture-of-Experts Neural Operator
- Controlling Transient Amplification Improves Long-horizon Rollouts
- Beyond Uniform Sampling: Synergistic Active Learning and Input Denoising for Robust Neural Operators
- Learned Coarse Models for Efficient Turbulence Simulation
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks