Cover Image

Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sankaran, Shyam, Wang, Hanwen, Perdikaris, Paris
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computational Physics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Simulating Three-dimensional Turbulence with Physics-informed Neural Networks
by: Wang, Sifan, et al.
Published: (2025)

Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective
by: Wang, Sifan, et al.
Published: (2025)

CFO: Learning Continuous-Time PDE Dynamics via Flow-Matched Neural Operators
by: Hou, Xianglong, et al.
Published: (2025)

Micrometer: Micromechanics Transformer for Predicting Mechanical Responses of Heterogeneous Materials
by: Wang, Sifan, et al.
Published: (2024)

Self-Flow-Matching assisted Full Waveform Inversion
by: Huang, Xinquan, et al.
Published: (2026)

Graph Neural PDE Solvers with Conservation and Similarity-Equivariance
by: Horie, Masanobu, et al.
Published: (2024)

Compositional Sparsity as an Inductive Bias for Neural Architecture Design
by: Lin, Hongyu, et al.
Published: (2026)

Physics-Informed Neural Networks and Extensions
by: Raissi, Maziar, et al.
Published: (2024)

On conditional diffusion models for PDE simulations
by: Shysheya, Aliaksandra, et al.
Published: (2024)

PhysicsCorrect: A Training-Free Approach for Stable Neural PDE Simulations
by: Huang, Xinquan, et al.
Published: (2025)

A Randomized PDE Energy driven Iterative Framework for Efficient and Stable PDE Solutions
by: Bing, Yi, et al.
Published: (2026)

Efficient High-Accuracy PDEs Solver with the Linear Attention Neural Operator
by: Zhong, Ming, et al.
Published: (2025)

Active Learning for Neural PDE Solvers
by: Musekamp, Daniel, et al.
Published: (2024)

LieSolver: A PDE-constrained solver for IBVPs using Lie symmetries
by: Klausen, René P., et al.
Published: (2025)

Composite Bayesian Optimization In Function Spaces Using NEON -- Neural Epistemic Operator Networks
by: Guilhoto, Leonardo Ferreira, et al.
Published: (2024)

Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks
by: Bencomo, Gianluca, et al.
Published: (2025)

CViT: Continuous Vision Transformer for Operator Learning
by: Wang, Sifan, et al.
Published: (2024)

Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solvers
by: Zhou, Hang, et al.
Published: (2024)

Ambient Physics: Training Neural PDE Solvers with Partial Observations
by: Majid, Harris Abdul, et al.
Published: (2026)

Generative Latent Neural PDE Solver using Flow Matching
by: Li, Zijie, et al.
Published: (2025)

On the Inductive Bias of Stacking Towards Improving Reasoning
by: Saunshi, Nikunj, et al.
Published: (2024)

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation
by: Li, Shanda, et al.
Published: (2025)

A Relational Inductive Bias for Dimensional Abstraction in Neural Networks
by: Campbell, Declan, et al.
Published: (2024)

Generative Neural Reparameterization for Differentiable PDE-constrained Optimization
by: Joglekar, Archis S.
Published: (2024)

Disk2Planet: A Robust and Automated Machine Learning Tool for Parameter Inference in Disk-Planet Systems
by: Mao, Shunyuan, et al.
Published: (2024)

Beyond Accuracy: EcoL2 Metric for Sustainable Neural PDE Solvers
by: Kapoor, Taniya, et al.
Published: (2025)

GEPS: Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
by: Koupaï, Armand Kassaï, et al.
Published: (2024)

Better Neural PDE Solvers Through Data-Free Mesh Movers
by: Hu, Peiyan, et al.
Published: (2023)

Training the Untrainable: Introducing Inductive Bias via Representational Alignment
by: Subramaniam, Vighnesh, et al.
Published: (2024)

Tensor-Compressed and Fully-Quantized Training of Neural PDE Solvers
by: Lu, Jinming, et al.
Published: (2025)

Learning Under Laws: A Constraint-Projected Neural PDE Solver that Eliminates Hallucinations
by: Singha, Mainak
Published: (2025)

Improving Generalization of Neural Vehicle Routing Problem Solvers Through the Lens of Model Architecture
by: Xiao, Yubin, et al.
Published: (2024)

Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs
by: Chen, Zihao, et al.
Published: (2025)

Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
by: Li, Zhuo, et al.
Published: (2025)

Deep Learning-Enhanced Preconditioning for Efficient Conjugate Gradient Solvers in Large-Scale PDE Systems
by: Li, Rui, et al.
Published: (2024)

MORPH: PDE Foundation Models with Arbitrary Data Modality
by: Rautela, Mahindra Singh, et al.
Published: (2025)

Multimodal Scientific Learning Beyond Diffusions and Flows
by: Guilhoto, Leonardo Ferreira, et al.
Published: (2026)

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
by: Gu, Yuxian, et al.
Published: (2025)

SPUS: A Lightweight and Parameter-Efficient Foundation Model for PDEs
by: Siddik, Abu Bucker, et al.
Published: (2025)

Differentiable Quantum Architecture Search in Quantum-Enhanced Neural Network Parameter Generation
by: Chen, Samuel Yen-Chi, et al.
Published: (2025)