{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1910.03193","title":"DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators","created":"2019-10-08","cited_by_count":2018},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2003.03485","title":"Neural Operator: Graph Kernel Network for Partial Differential Equations","created":"2020-03-07","cited_by_count":734},{"id":"2109.01050","title":"Characterizing possible failure modes in physics-informed neural networks","created":"2021-09-02","cited_by_count":643},{"id":"2007.14527","title":"When and why PINNs fail to train: A neural tangent kernel perspective","created":"2020-07-28","cited_by_count":634},{"id":"1907.04502","title":"DeepXDE: A deep learning library for solving differential equations","created":"2019-07-10","cited_by_count":619},{"id":"1710.00211","title":"The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems","created":"2017-09-30","cited_by_count":583},{"id":"2103.10974","title":"Learning the solution operator of parametric partial differential equations with physics-informed DeepOnets","created":"2021-03-19","cited_by_count":540},{"id":"2207.05209","title":"Fourier Neural Operator with Learned Deformations for PDEs on General Geometries","created":"2022-07-11","cited_by_count":427},{"id":"2202.03376","title":"Message Passing Neural PDE Solvers","created":"2022-02-07","cited_by_count":386},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2006.09535","title":"Multipole Graph Neural Operator for Parametric Partial Differential Equations","created":"2020-06-16","cited_by_count":349},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343},{"id":"2302.14376","title":"GNOT: A General Neural Operator Transformer for Operator Learning","created":"2023-02-28","cited_by_count":336},{"id":"2402.02366","title":"Transolver: A Fast Transformer Solver for PDEs on General Geometries","created":"2024-02-04","cited_by_count":326},{"id":"2309.00583","title":"Geometry-Informed Neural Operator for Large-Scale 3D PDEs","created":"2023-09-01","cited_by_count":303},{"id":"2109.03697","title":"U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flow","created":"2021-09-03","cited_by_count":297},{"id":"2205.13671","title":"Transformer for Partial Differential Equations' Operator Learning","created":"2022-05-26","cited_by_count":283},{"id":"2111.13802","title":"Factorized Fourier Neural Operators","created":"2021-11-27","cited_by_count":249},{"id":"2109.13459","title":"Multiwavelet-based Operator Learning for Differential Equations","created":"2021-09-28","cited_by_count":234},{"id":"2306.03838","title":"Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere","created":"2023-06-06","cited_by_count":233},{"id":"2204.11127","title":"U-NO: U-shaped Neural Operators","created":"2022-04-23","cited_by_count":230},{"id":"2309.15325","title":"Neural Operators for Accelerating Scientific Simulations and Design","created":"2023-09-27","cited_by_count":221},{"id":"2202.06137","title":"MIONet: Learning multiple-input operators via tensor product","created":"2022-02-12","cited_by_count":181},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128},{"id":"2201.01032","title":"Learning Operators with Coupled Attention","created":"2022-01-04","cited_by_count":90},{"id":"2312.08874","title":"Agent Attention: On the Integration of Softmax and Linear Attention","created":"2023-12-14","cited_by_count":90},{"id":"2301.12664","title":"Solving High-Dimensional PDEs with Latent Spectral Models","created":"2023-01-30","cited_by_count":89},{"id":"2206.03551","title":"NOMAD: Nonlinear Manifold Decoders for Operator Learning","created":"2022-06-07","cited_by_count":83},{"id":"2406.03923","title":"Latent Neural Operator for Solving Forward and Inverse PDE Problems","created":"2024-06-06","cited_by_count":80},{"id":"2106.04781","title":"Encoding physics to learn reaction-diffusion processes","created":"2021-06-09","cited_by_count":61},{"id":"2310.12487","title":"Improved Operator Learning by Orthogonal Attention","created":"2023-10-19","cited_by_count":61},{"id":"2405.13998","title":"CViT: Continuous Vision Transformer for Operator Learning","created":"2024-05-22","cited_by_count":51},{"id":"2210.10890","title":"Mitigating spectral bias for the multiscale operator learning","created":"2022-10-19","cited_by_count":44},{"id":"2304.13221","title":"Nonlocality and Nonlinearity Implies Universality in Operator Learning","created":"2023-04-26","cited_by_count":43},{"id":"2310.19809","title":"MgNO: Efficient Parameterization of Linear Operators via Multigrid","created":"2023-10-16","cited_by_count":40},{"id":"2405.19166","title":"Transformers as Neural Operators for Solutions of Differential Equations with Finite Regularity","created":"2024-05-29","cited_by_count":34},{"id":"2301.10022","title":"Koopman neural operator as a mesh-free solver of non-linear partial differential equations","created":"2023-01-24","cited_by_count":29},{"id":"2303.08891","title":"ViTO: Vision Transformer-Operator","created":"2023-03-15","cited_by_count":29},{"id":"2502.11835","title":"Neural Chaos: A Spectral Stochastic Neural Operator","created":"2025-02-17","cited_by_count":21},{"id":"2308.04690","title":"Finite Element Operator Network for Solving Elliptic-type parametric PDEs","created":"2023-08-09","cited_by_count":14},{"id":"2310.17844","title":"Adaptive operator learning for infinite-dimensional Bayesian inverse problems","created":"2023-10-27","cited_by_count":11},{"id":"2410.11382","title":"Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space","created":"2024-10-15","cited_by_count":10}],"next_cursor":null}