{"list":"other","total":83,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"1806.03536","title":"Representation Learning on Graphs with Jumping Knowledge Networks","created":"2018-06-09","cited_by_count":877},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2003.00982","title":"Benchmarking Graph Neural Networks","created":"2020-03-02","cited_by_count":680},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"2006.07988","title":"Adaptive Universal Generalized PageRank Graph Neural Network","created":"2020-06-14","cited_by_count":595},{"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":"1911.05485","title":"Diffusion Improves Graph Learning","created":"2019-10-28","cited_by_count":414},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"1909.03496","title":"Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks","created":"2019-09-08","cited_by_count":272},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260},{"id":"2006.13318","title":"A Note on Over-Smoothing for Graph Neural Networks","created":"2020-06-23","cited_by_count":249},{"id":"2303.10993","title":"A Survey on Oversmoothing in Graph Neural Networks","created":"2023-03-20","cited_by_count":247},{"id":"1905.12374","title":"GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series","created":"2019-05-29","cited_by_count":231},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161},{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"2205.12156","title":"Not too little, not too much: a theoretical analysis of graph (over)smoothing","created":"2022-05-24","cited_by_count":106},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"2207.02971","title":"Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding","created":"2022-07-06","cited_by_count":91},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83},{"id":"2204.00993","title":"Improving Vision Transformers by Revisiting High-frequency Components","created":"2022-04-03","cited_by_count":76},{"id":"1307.0468","title":"Discrete Signal Processing on Graphs: Frequency Analysis","created":"2013-07-01","cited_by_count":73},{"id":"2202.08625","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","created":"2022-02-17","cited_by_count":72},{"id":"2002.08653","title":"Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree","created":"2020-02-20","cited_by_count":69},{"id":"2211.14208","title":"GREAD: Graph Neural Reaction-Diffusion Networks","created":"2022-11-25","cited_by_count":54},{"id":"2009.14332","title":"Multi-hop Attention Graph Neural Network","created":"2020-09-29","cited_by_count":53},{"id":"2212.10701","title":"A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks","created":"2022-12-21","cited_by_count":49},{"id":"2305.16102","title":"Demystifying Oversmoothing in Attention-Based Graph Neural Networks","created":"2023-05-25","cited_by_count":49},{"id":"2304.06446","title":"SpectFormer: Frequency and Attention is what you need in a Vision Transformer","created":"2023-04-13","cited_by_count":48},{"id":"2104.12753","title":"Vision Transformers with Patch Diversification","created":"2021-04-26","cited_by_count":45},{"id":"2305.13084","title":"A Fractional Graph Laplacian Approach to Oversmoothing","created":"2023-05-22","cited_by_count":45},{"id":"2103.04886","title":"Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks","created":"2021-03-08","cited_by_count":39},{"id":"2303.06562","title":"ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond","created":"2023-03-12","cited_by_count":39},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39},{"id":"2106.03714","title":"Refiner: Refining Self-attention for Vision Transformers","created":"2021-06-07","cited_by_count":38},{"id":"2203.06345","title":"The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy","created":"2022-03-12","cited_by_count":35},{"id":"2312.00751","title":"Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals","created":"2023-12-01","cited_by_count":32},{"id":"1811.11934","title":"Multi-granularity hierarchical attention fusion networks for reading comprehension and question answering","created":"2018-11-29","cited_by_count":28},{"id":"2008.00586","title":"Signal Processing on Directed Graphs","created":"2020-08-02","cited_by_count":28},{"id":"1701.02720","title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","created":"2017-01-10","cited_by_count":24},{"id":"2111.09714","title":"You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling","created":"2021-11-18","cited_by_count":17},{"id":"2311.01310","title":"Scattering Vision Transformer: Spectral Mixing Matters","created":"2023-11-02","cited_by_count":17},{"id":"2305.06154","title":"Alleviating Over-smoothing for Unsupervised Sentence Representation","created":"2023-05-09","cited_by_count":16},{"id":"2208.11790","title":"Addressing Token Uniformity in Transformers via Singular Value Transformation","created":"2022-08-24","cited_by_count":14},{"id":"2211.11586","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","created":"2022-11-17","cited_by_count":11},{"id":"2205.09335","title":"A Simple Yet Effective SVD-GCN for Directed Graphs","created":"2022-05-19","cited_by_count":7},{"id":"2306.01610","title":"Centered Self-Attention Layers","created":"2023-06-02","cited_by_count":7}],"next_cursor":null}