{"list":"other","total":66,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1706.06978","title":"Deep Interest Network for Click-Through Rate Prediction","created":"2017-06-21","cited_by_count":544},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"2005.04345","title":"An Investigation of Why Overparameterization Exacerbates Spurious Correlations","created":"2020-05-09","cited_by_count":310},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196},{"id":"2006.04710","title":"The Lipschitz Constant of Self-Attention","created":"2020-06-08","cited_by_count":174},{"id":"2111.13824","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","created":"2021-11-27","cited_by_count":151},{"id":"2104.10858","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","created":"2021-04-22","cited_by_count":144},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144},{"id":"2006.14548","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","created":"2020-06-25","cited_by_count":143},{"id":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133},{"id":"1905.06874","title":"Behavior Sequence Transformer for E-commerce Recommendation in Alibaba","created":"2019-05-15","cited_by_count":130},{"id":"1906.04688","title":"An Improved Analysis of Training Over-parameterized Deep Neural Networks","created":"2019-06-11","cited_by_count":121},{"id":"2006.10540","title":"Infinite attention: NNGP and NTK for deep attention networks","created":"2020-06-18","cited_by_count":121},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119},{"id":"2005.10190","title":"Feature Purification: How Adversarial Training Performs Robust Deep Learning","created":"2020-05-20","cited_by_count":107},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102},{"id":"1706.03175","title":"Recovery Guarantees for One-hidden-layer Neural Networks","created":"2017-06-10","cited_by_count":94},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93},{"id":"1905.10337","title":"What Can ResNet Learn Efficiently, Going Beyond Kernels?","created":"2019-05-24","cited_by_count":91},{"id":"2006.09286","title":"On the Computational Power of Transformers and its Implications in Sequence Modeling","created":"2020-06-16","cited_by_count":85},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79},{"id":"2002.07400","title":"Learning Parities with Neural Networks","created":"2020-02-18","cited_by_count":78},{"id":"2206.01717","title":"A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features","created":"2022-06-03","cited_by_count":49},{"id":"2106.03143","title":"CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings","created":"2021-06-06","cited_by_count":47},{"id":"2106.03764","title":"On the Expressive Power of Self-Attention Matrices","created":"2021-06-07","cited_by_count":47},{"id":"2007.02876","title":"A Mathematical Theory of Attention","created":"2020-07-06","cited_by_count":46},{"id":"2006.12467","title":"The Depth-to-Width Interplay in Self-Attention","created":"2020-06-22","cited_by_count":42},{"id":"2103.07601","title":"Approximating How Single Head Attention Learns","created":"2021-03-13","cited_by_count":38},{"id":"2201.07703","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","created":"2022-01-19","cited_by_count":37},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37},{"id":"2201.12083","title":"DynaMixer: A Vision MLP Architecture with Dynamic Mixing","created":"2022-01-28","cited_by_count":28},{"id":"2203.09064","title":"Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning","created":"2022-03-17","cited_by_count":27},{"id":"2006.14117","title":"Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case","created":"2020-06-25","cited_by_count":24},{"id":"2207.03584","title":"Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling","created":"2022-07-07","cited_by_count":23},{"id":"1802.06463","title":"Guaranteed Recovery of One-Hidden-Layer Neural Networks via Cross Entropy","created":"2018-02-18","cited_by_count":22},{"id":"2302.02922","title":"Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks","created":"2023-02-06","cited_by_count":16},{"id":"1711.03440","title":"Learning Non-overlapping Convolutional Neural Networks with Multiple Kernels","created":"2017-11-08","cited_by_count":14},{"id":"2207.03615","title":"Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data","created":"2022-07-07","cited_by_count":8}],"next_cursor":null}