{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","cited_by_count":368},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"2106.15772","title":"A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers","created":"2021-06-30","cited_by_count":318},{"id":"2008.00401","title":"Multilingual Translation with Extensible Multilingual Pretraining and Finetuning","created":"2020-08-02","cited_by_count":287},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1907.05019","title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","created":"2019-07-11","cited_by_count":257},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1906.08230","title":"Evaluating Protein Transfer Learning with TAPE","created":"2019-06-19","cited_by_count":231},{"id":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","created":"2020-09-18","cited_by_count":182},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121},{"id":"2002.10365","title":"The Early Phase of Neural Network Training","created":"2020-02-24","cited_by_count":115},{"id":"2203.07259","title":"The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models","created":"2022-03-14","cited_by_count":115},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"id":"2011.04946","title":"When Do You Need Billions of Words of Pretraining Data?","created":"2020-11-10","cited_by_count":104},{"id":"1912.04427","title":"Winning the Lottery with Continuous Sparsification","created":"2019-12-10","cited_by_count":100},{"id":"1905.05934","title":"EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis","created":"2019-05-15","cited_by_count":98},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"2206.12562","title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","created":"2022-06-25","cited_by_count":79},{"id":"1805.08941","title":"AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference","created":"2018-05-23","cited_by_count":77},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75},{"id":"1810.09619","title":"Sparse DNNs with Improved Adversarial Robustness","created":"2018-10-23","cited_by_count":72},{"id":"2111.05754","title":"Prune Once for All: Sparse Pre-Trained Language Models","created":"2021-11-10","cited_by_count":66},{"id":"2006.09081","title":"Progressive Skeletonization: Trimming more fat from a network at initialization","created":"2020-06-16","cited_by_count":64},{"id":"2106.09129","title":"A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness","created":"2021-06-16","cited_by_count":62},{"id":"2107.03356","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","created":"2021-07-07","cited_by_count":54},{"id":"2110.00296","title":"Powerpropagation: A sparsity inducing weight reparameterisation","created":"2021-10-01","cited_by_count":49},{"id":"2106.14568","title":"Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity","created":"2021-06-28","cited_by_count":44},{"id":"2202.09844","title":"Sparsity Winning Twice: Better Robust Generalization from More Efficient Training","created":"2022-02-20","cited_by_count":41},{"id":"2104.08682","title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","created":"2021-04-18","cited_by_count":40},{"id":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25},{"id":"2110.07431","title":"Towards More Effective and Economic Sparsely-Activated Model","created":"2021-10-14","cited_by_count":11},{"id":"2208.10842","title":"Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost","created":"2022-08-23","cited_by_count":11},{"id":"1812.10240","title":"Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning","created":"2018-12-26","cited_by_count":6}],"next_cursor":null}