{"list":"other","total":63,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"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":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"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":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"2002.11296","title":"Sparse Sinkhorn Attention","created":"2020-02-26","cited_by_count":251},{"id":"2004.04037","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","created":"2020-04-08","cited_by_count":251},{"id":"2012.09852","title":"SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning","created":"2020-12-17","cited_by_count":234},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"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":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"1707.01213","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","created":"2017-07-05","cited_by_count":181},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"1903.12136","title":"Distilling Task-Specific Knowledge from BERT into Simple Neural Networks","created":"2019-03-28","cited_by_count":153},{"id":"2009.12812","title":"TernaryBERT: Distillation-aware Ultra-low Bit BERT","created":"2020-09-27","cited_by_count":148},{"id":"2004.07320","title":"Training with Quantization Noise for Extreme Model Compression","created":"2020-04-15","cited_by_count":145},{"id":"2007.04825","title":"Fast Transformers with Clustered Attention","created":"2020-07-09","cited_by_count":123},{"id":"2004.03844","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","created":"2020-04-08","cited_by_count":118},{"id":"2005.00561","title":"When BERT Plays the Lottery, All Tickets Are Winning","created":"2020-05-01","cited_by_count":114},{"id":"2005.03842","title":"GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference","created":"2020-05-08","cited_by_count":106},{"id":"2005.07093","title":"Bayesian Bits: Unifying Quantization and Pruning","created":"2020-05-14","cited_by_count":94},{"id":"2004.12406","title":"Masking as an Efficient Alternative to Finetuning for Pretrained Language Models","created":"2020-04-26","cited_by_count":93},{"id":"2010.07003","title":"Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search","created":"2020-10-14","cited_by_count":76},{"id":"1906.02768","title":"Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP","created":"2019-06-06","cited_by_count":73},{"id":"2002.04809","title":"Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning","created":"2020-02-12","cited_by_count":61},{"id":"1906.00532","title":"Efficient 8-Bit Quantization of Transformer Neural Machine Language Translation Model","created":"2019-06-03","cited_by_count":59},{"id":"2006.11316","title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","created":"2020-06-19","cited_by_count":50},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45},{"id":"2105.11618","title":"TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference","created":"2021-05-25","cited_by_count":40},{"id":"1711.02782","title":"Block-Sparse Recurrent Neural Networks","created":"2017-11-08","cited_by_count":39},{"id":"2009.08065","title":"Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning","created":"2020-09-17","cited_by_count":39},{"id":"2010.01791","title":"Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior","created":"2020-10-05","cited_by_count":23},{"id":"1709.05027","title":"Learning Intrinsic Sparse Structures within Long Short-Term Memory","created":"2017-09-15","cited_by_count":18},{"id":"2005.06628","title":"schuBERT: Optimizing Elements of BERT","created":"2020-05-09","cited_by_count":17}],"next_cursor":null}