Imagen de Portada

From Cheap Geometry to Expensive Physics: Elevating Neural Operators via Latent Shape Pretraining

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Zhizhou, Wu, Youjia, Zhang, Kaixuan, Wang, Yanjia
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving
por: Huang, Jianing, et al.
Publicado: (2025)

Latent Neural Operator Pretraining for Solving Time-Dependent PDEs
por: Wang, Tian, et al.
Publicado: (2024)

AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive
por: Guo, Taicheng, et al.
Publicado: (2026)

Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving
por: Su, Chang, et al.
Publicado: (2026)

Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators
por: Cheng, Ze, et al.
Publicado: (2025)

Strategies for Pretraining Neural Operators
por: Zhou, Anthony, et al.
Publicado: (2024)

Geometric Neural Operators via Lie Group-Constrained Latent Dynamics
por: Zhang, Jiaquan, et al.
Publicado: (2026)

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search
por: Robertson, John T., et al.
Publicado: (2026)

Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations
por: Cheng, Ze, et al.
Publicado: (2024)

Physics-Informed Geometry-Aware Neural Operator
por: Zhong, Weiheng, et al.
Publicado: (2024)

Geometry-Aware Neural Optimizer for Shape Optimization and Inversion
por: Sun, Guoze, et al.
Publicado: (2026)

Pretraining a Neural Operator in Lower Dimensions
por: Hemmasian, AmirPouya, et al.
Publicado: (2024)

Beyond Dense States: Elevating Sparse Transcoders to Active Operators for Latent Reasoning
por: Wang, Yadong, et al.
Publicado: (2026)

Preconditioning for Physics-Informed Neural Networks
por: Liu, Songming, et al.
Publicado: (2024)

Towards Universal Neural Operators through Multiphysics Pretraining
por: Masliaev, Mikhail, et al.
Publicado: (2025)

How Neural Losses Shape VAE Latents
por: Strano, Giorgio, et al.
Publicado: (2026)

ATOM: A Pretrained Neural Operator for Multitask Molecular Dynamics
por: Thompson, Luke, et al.
Publicado: (2025)

Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs
por: Rahman, Md Ashiqur, et al.
Publicado: (2024)

Surrogate Ensemble in Expensive Multi-Objective Optimization via Deep Q-Learning
por: Wu, Yuxin, et al.
Publicado: (2026)

Learning Neural Operators from Partial Observations via Latent Autoregressive Modeling
por: Hou, Jingren, et al.
Publicado: (2026)

PGOT: A Physics-Geometry Operator Transformer for Complex PDEs
por: Zhang, Zhuo, et al.
Publicado: (2025)

Understanding Latent Diffusability via Fisher Geometry
por: Gu, Jing, et al.
Publicado: (2026)

Connecting Neural Models Latent Geometries with Relative Geodesic Representations
por: Yu, Hanlin, et al.
Publicado: (2025)

Latent Neural Operator for Solving Forward and Inverse PDE Problems
por: Wang, Tian, et al.
Publicado: (2024)

Geometry-Informed Neural Operator Transformer
por: Liu, Qibang, et al.
Publicado: (2025)

DeepONet as a Multi-Operator Extrapolation Model: Distributed Pretraining with Physics-Informed Fine-Tuning
por: Zhang, Zecheng, et al.
Publicado: (2024)

Multifidelity Simulation-based Inference for Computationally Expensive Simulators
por: Krouglova, Anastasia N., et al.
Publicado: (2025)

Efficient MCMC Sampling with Expensive-to-Compute and Irregular Likelihoods
por: Rosato, Conor, et al.
Publicado: (2025)

Experience-Based Evolutionary Algorithms for Expensive Optimization
por: Yu, Xunzhao, et al.
Publicado: (2023)

Do Neural Operators Forget Geometry? The Forgetting Hypothesis in Deep Operator Learning
por: Xia, Yanming, et al.
Publicado: (2026)

Cheap Bootstrap for Fast Uncertainty Quantification of Stochastic Gradient Descent
por: Lam, Henry, et al.
Publicado: (2023)

Physics-Informed Latent Neural Operator for Real-time Predictions of time-dependent parametric PDEs
por: Karumuri, Sharmila, et al.
Publicado: (2025)

Pretraining Strategy for Neural Potentials
por: Zhang, Zehua, et al.
Publicado: (2024)

Continuous Geometry-Aware Graph Diffusion via Hyperbolic Neural PDE
por: Liu, Jiaxu, et al.
Publicado: (2024)

Relative Geometry of Neural Forecasters: Linking Accuracy and Alignment in Learned Latent Geometry
por: Kucukahmetler, Deniz, et al.
Publicado: (2026)

Physics-Informed Neural Networks and Neural Operators for Parametric PDEs
por: Zhang, Zhuo, et al.
Publicado: (2025)

FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimization
por: Yao, Yiming, et al.
Publicado: (2025)

Harnessing Scale and Physics: A Multi-Graph Neural Operator Framework for PDEs on Arbitrary Geometries
por: Li, Zhihao, et al.
Publicado: (2024)

Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries
por: Borde, Haitz Sáez de Ocáriz, et al.
Publicado: (2023)

From Logits to Latents: Contrastive Representation Shaping for LLM Unlearning
por: Tang, Haoran, et al.
Publicado: (2026)