{"list":"other","total":84,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"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":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"2406.11794","title":"DataComp-LM: In search of the next generation of training sets for language models","created":"2024-06-17","cited_by_count":398},{"id":"2305.19860","title":"A Survey on Large Language Models for Recommendation","created":"2023-05-31","cited_by_count":379},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1803.00942","title":"Not All Samples Are Created Equal: Deep Learning with Importance Sampling","created":"2018-03-02","cited_by_count":328},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"id":"1502.04759","title":"Coordinate Descent Algorithms","created":"2015-02-17","cited_by_count":219},{"id":"2409.14485","title":"Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding","created":"2024-09-22","cited_by_count":213},{"id":"1903.06059","title":"Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement","created":"2019-03-14","cited_by_count":211},{"id":"1708.07860","title":"Multi-task Self-Supervised Visual Learning","created":"2017-08-25","cited_by_count":200},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"2307.03576","title":"One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention","created":"2023-07-07","cited_by_count":170},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"2401.04925","title":"The Impact of Reasoning Step Length on Large Language Models","created":"2024-01-10","cited_by_count":153},{"id":"1704.07520","title":"Stein Variational Gradient Descent as Gradient Flow","created":"2017-04-25","cited_by_count":152},{"id":"1910.12478","title":"Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes","created":"2019-10-28","cited_by_count":151},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122},{"id":"2006.10540","title":"Infinite attention: NNGP and NTK for deep attention networks","created":"2020-06-18","cited_by_count":121},{"id":"1902.02181","title":"Attention in Natural Language Processing","created":"2019-02-04","cited_by_count":101},{"id":"2106.03149","title":"Large-scale Unsupervised Semantic Segmentation","created":"2021-06-06","cited_by_count":101},{"id":"1601.08169","title":"Kernels for sequentially ordered data","created":"2016-01-29","cited_by_count":84},{"id":"2003.12909","title":"Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning","created":"2020-03-28","cited_by_count":81},{"id":"2101.00063","title":"EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets","created":"2020-12-31","cited_by_count":79},{"id":"2007.01580","title":"On the Similarity between the Laplace and Neural Tangent Kernels","created":"2020-07-03","cited_by_count":76},{"id":"1910.05821","title":"Policy Poisoning in Batch Reinforcement Learning and Control","created":"2019-10-13","cited_by_count":70},{"id":"2302.04460","title":"Bag of Tricks for Training Data Extraction from Language Models","created":"2023-02-09","cited_by_count":70},{"id":"1801.05927","title":"An Overview of Machine Teaching","created":"2018-01-18","cited_by_count":63},{"id":"2308.01045","title":"Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation","created":"2023-08-02","cited_by_count":62},{"id":"2307.14023","title":"Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?","created":"2023-07-26","cited_by_count":47},{"id":"1705.10470","title":"Iterative Machine Teaching","created":"2017-05-30","cited_by_count":41},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37},{"id":"2404.10830","title":"Fewer Truncations Improve Language Modeling","created":"2024-04-16","cited_by_count":35},{"id":"1402.2092","title":"Near-Optimally Teaching the Crowd to Classify","created":"2014-02-10","cited_by_count":32},{"id":"2401.10446","title":"Large Language Models are Efficient Learners of Noise-Robust Speech Recognition","created":"2024-01-19","cited_by_count":31},{"id":"2309.00121","title":"Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation","created":"2023-08-31","cited_by_count":30},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29},{"id":"1710.07742","title":"Towards Black-box Iterative Machine Teaching","created":"2017-10-21","cited_by_count":20},{"id":"1903.00765","title":"Weakly Labelled AudioSet Tagging with Attention Neural Networks","created":"2019-03-02","cited_by_count":17},{"id":"2409.19696","title":"Vision-Language Models are Strong Noisy Label Detectors","created":"2024-09-29","cited_by_count":16},{"id":"2405.10531","title":"Nonparametric Teaching of Implicit Neural Representations","created":"2024-05-17","cited_by_count":15},{"id":"1901.07114","title":"Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits","created":"2019-01-21","cited_by_count":13},{"id":"1804.06481","title":"Unlearn What You Have Learned: Adaptive Crowd Teaching with Exponentially Decayed Memory Learners","created":"2018-04-17","cited_by_count":11},{"id":"2305.15273","title":"Revisiting Token Dropping Strategy in Efficient BERT Pretraining","created":"2023-05-24","cited_by_count":11},{"id":"2306.03007","title":"Nonparametric Iterative Machine Teaching","created":"2023-06-05","cited_by_count":9},{"id":"2311.10318","title":"Nonparametric Teaching for Multiple Learners","created":"2023-11-17","cited_by_count":7},{"id":"2406.00427","title":"You Only Need Less Attention at Each Stage in Vision Transformers","created":"2024-06-01","cited_by_count":7},{"id":"2505.14170","title":"Nonparametric Teaching for Graph Property Learners","created":"2025-05-20","cited_by_count":5},{"id":"2306.12070","title":"Task-Robust Pre-Training for Worst-Case Downstream Adaptation","created":"2023-06-21","cited_by_count":3},{"id":"2511.15487","title":"NTK-Guided Implicit Neural Teaching","created":"2025-11-19","cited_by_count":2}],"next_cursor":null}