Do Neural PDE Solvers Learn the Right Dynamics?
cs.LG, nlin.CD
Submitted: 2026-10-03
Updated: 2026-10-03
Sources
- Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers
- Towards Multi-spatiotemporal-scale Generalized PDE Modeling
- DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
- Fourier Neural Operator for Parametric Partial Differential Equations
- Towards Stability of Autoregressive Neural Operators
- Generative AI for fast and accurate statistical computation of fluids
- DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems
- TRIE: An Evaluation Framework for Stochastic PDE Surrogates
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks