SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining
cs.LG, cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
Terminology
Sources
- Retraining-Free Merging of Sparse MoE via Hierarchical Clustering
- OmniArch: Building Foundation Model For Scientific Computing
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- 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
- Gaussian Error Linear Units (GELUs)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Mixtral of Experts
- Fourier Neural Operator for Parametric Partial Differential Equations
- Transformer for Partial Differential Equations' Operator Learning
- CFDBench: A Large-Scale Benchmark for Machine Learning Methods in Fluid Dynamics
- Multiple Physics Pretraining for Physical Surrogate Models
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
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