{"list":"other","total":72,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2010.03409","title":"Learning Mesh-Based Simulation with Graph Networks","created":"2020-10-07","cited_by_count":868},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2202.11214","title":"FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators","created":"2022-02-22","cited_by_count":776},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1708.07469","title":"DGM: A deep learning algorithm for solving partial differential equations","created":"2017-08-24","cited_by_count":678},{"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":"1707.02568","title":"Solving high-dimensional partial differential equations using deep learning","created":"2017-07-09","cited_by_count":556},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2111.03794","title":"Physics-Informed Neural Operator for Learning Partial Differential Equations","created":"2021-11-06","cited_by_count":527},{"id":"1712.04851","title":"Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification","created":"2017-12-13","cited_by_count":521},{"id":"1712.09707","title":"Deep learning for universal linear embeddings of nonlinear dynamics","created":"2017-12-27","cited_by_count":494},{"id":"2102.01010","title":"Machine learning accelerated computational fluid dynamics","created":"2021-01-28","cited_by_count":471},{"id":"2108.08481","title":"Neural Operator: Learning Maps Between Function Spaces","created":"2021-08-19","cited_by_count":414},{"id":"2210.07182","title":"PDEBENCH: An Extensive Benchmark for Scientific Machine Learning","created":"2022-10-13","cited_by_count":413},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"2001.04385","title":"Universal Differential Equations for Scientific Machine Learning","created":"2020-01-13","cited_by_count":353},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343},{"id":"2010.09885","title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction","created":"2020-10-19","cited_by_count":337},{"id":"2301.10343","title":"ClimaX: A foundation model for weather and climate","created":"2023-01-24","cited_by_count":337},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250},{"id":"2007.00016","title":"Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers","created":"2020-06-30","cited_by_count":205},{"id":"2209.15616","title":"Towards Multi-spatiotemporal-scale Generalized PDE Modeling","created":"2022-09-30","cited_by_count":197},{"id":"2208.06677","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","created":"2022-08-13","cited_by_count":174},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150},{"id":"2306.00258","title":"Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior","created":"2023-06-01","cited_by_count":131},{"id":"2301.07733","title":"Learning-Rate-Free Learning by D-Adaptation","created":"2023-01-18","cited_by_count":113},{"id":"2112.15275","title":"Learned Coarse Models for Efficient Turbulence Simulation","created":"2021-12-31","cited_by_count":91},{"id":"2203.09795","title":"Three things everyone should know about Vision Transformers","created":"2022-03-18","cited_by_count":90},{"id":"2204.09810","title":"Deep transfer operator learning for partial differential equations under conditional shift","created":"2022-04-20","cited_by_count":83},{"id":"2302.04107","title":"Can Physics-Informed Neural Networks beat the Finite Element Method?","created":"2023-02-08","cited_by_count":68},{"id":"2203.01360","title":"Neural Galerkin Schemes with Active Learning for High-Dimensional Evolution Equations","created":"2022-03-02","cited_by_count":56},{"id":"2110.11286","title":"One-Shot Transfer Learning of Physics-Informed Neural Networks","created":"2021-10-21","cited_by_count":49},{"id":"2207.00556","title":"Learning to correct spectral methods for simulating turbulent flows","created":"2022-07-01","cited_by_count":49},{"id":"2309.06126","title":"AstroLLaMA: Towards Specialized Foundation Models in Astronomy","created":"2023-09-12","cited_by_count":41},{"id":"1811.06533","title":"Learning to Predict the Cosmological Structure Formation","created":"2018-11-15","cited_by_count":38},{"id":"2304.14118","title":"Learning Neural PDE Solvers with Parameter-Guided Channel Attention","created":"2023-04-27","cited_by_count":38},{"id":"2104.10873","title":"Mosaic Flows: A Transferable Deep Learning Framework for Solving PDEs on Unseen Domains","created":"2021-04-22","cited_by_count":37},{"id":"2302.05738","title":"Cross-Modal Fine-Tuning: Align then Refine","created":"2023-02-11","cited_by_count":34},{"id":"1904.05417","title":"Unsupervised Deep Learning Algorithm for PDE-based Forward and Inverse Problems","created":"2019-04-10","cited_by_count":31},{"id":"2307.05432","title":"Self-Supervised Learning with Lie Symmetries for Partial Differential Equations","created":"2023-07-11","cited_by_count":29},{"id":"2212.04663","title":"Transfer Learning Enhanced DeepONet for Long-Time Prediction of Evolution Equations","created":"2022-12-09","cited_by_count":28},{"id":"2206.03198","title":"Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow","created":"2022-06-07","cited_by_count":20},{"id":"2101.04117","title":"A Bayesian neural network predicts the dissolution of compact planetary systems","created":"2021-01-11","cited_by_count":15},{"id":"2206.04594","title":"Field Level Neural Network Emulator for Cosmological N-body Simulations","created":"2022-06-09","cited_by_count":13},{"id":"2208.03498","title":"Deep Learning Closure Models for Large-Eddy Simulation of Flows around Bluff Bodies","created":"2022-08-06","cited_by_count":11}],"next_cursor":null}