{"list":"other","total":91,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"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":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"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":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"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":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1404.0736","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","created":"2014-04-02","cited_by_count":306},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1911.03852","title":"HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks","created":"2019-11-10","cited_by_count":261},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"1903.09291","title":"Towards Optimal Structured CNN Pruning via Generative Adversarial Learning","created":"2019-03-22","cited_by_count":146},{"id":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"2006.10901","title":"Sparse GPU Kernels for Deep Learning","created":"2020-06-18","cited_by_count":141},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131},{"id":"2010.07611","title":"Layer-adaptive sparsity for the Magnitude-based Pruning","created":"2020-10-15","cited_by_count":126},{"id":"1812.00090","title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search","created":"2018-11-30","cited_by_count":125},{"id":"1705.08665","title":"Bayesian Compression for Deep Learning","created":"2017-05-24","cited_by_count":116},{"id":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"2006.08509","title":"APQ: Joint Search for Network Architecture, Pruning and Quantization Policy","created":"2020-06-15","cited_by_count":99},{"id":"1911.07412","title":"Provable Filter Pruning for Efficient Neural Networks","created":"2019-11-18","cited_by_count":98},{"id":"2002.11985","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","created":"2020-02-27","cited_by_count":96},{"id":"1801.05787","title":"Faster gaze prediction with dense networks and Fisher pruning","created":"2018-01-17","cited_by_count":94},{"id":"2005.07093","title":"Bayesian Bits: Unifying Quantization and Pruning","created":"2020-05-14","cited_by_count":94},{"id":"1802.04680","title":"Training and Inference with Integers in Deep Neural Networks","created":"2018-02-13","cited_by_count":86},{"id":"1911.09723","title":"Fast Sparse ConvNets","created":"2019-11-21","cited_by_count":86},{"id":"2006.10159","title":"Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors","created":"2020-06-15","cited_by_count":80},{"id":"1912.12607","title":"Towards Unified INT8 Training for Convolutional Neural Network","created":"2019-12-29","cited_by_count":79},{"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":"1808.08271","title":"An elementary introduction to information geometry","created":"2018-08-17","cited_by_count":76},{"id":"1810.01109","title":"AI Benchmark: Running Deep Neural Networks on Android Smartphones","created":"2018-10-02","cited_by_count":75},{"id":"1703.08651","title":"More is Less: A More Complicated Network with Less Inference Complexity","created":"2017-03-25","cited_by_count":66},{"id":"1902.05690","title":"AutoQ: Automated Kernel-Wise Neural Network Quantization","created":"2019-02-15","cited_by_count":63},{"id":"1802.10399","title":"Compressing Neural Networks using the Variational Information Bottleneck","created":"2018-02-28","cited_by_count":59},{"id":"2107.03356","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","created":"2021-07-07","cited_by_count":54},{"id":"2203.08368","title":"Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance","created":"2022-03-16","cited_by_count":54},{"id":"2111.13445","title":"How Well Do Sparse Imagenet Models Transfer?","created":"2021-11-26","cited_by_count":50},{"id":"2007.10463","title":"Differentiable Joint Pruning and Quantization for Hardware Efficiency","created":"2020-07-20","cited_by_count":46},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45},{"id":"2109.07865","title":"OMPQ: Orthogonal Mixed Precision Quantization","created":"2021-09-16","cited_by_count":39},{"id":"1710.07739","title":"Learning Discrete Weights Using the Local Reparameterization Trick","created":"2017-10-21","cited_by_count":29},{"id":"2302.05397","title":"A Practical Mixed Precision Algorithm for Post-Training Quantization","created":"2023-02-10","cited_by_count":24},{"id":"1811.10559","title":"Leveraging Filter Correlations for Deep Model Compression","created":"2018-11-26","cited_by_count":23},{"id":"2105.10533","title":"BCNet: Searching for Network Width with Bilaterally Coupled Network","created":"2021-05-21","cited_by_count":23},{"id":"2205.11141","title":"OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization","created":"2022-05-23","cited_by_count":19},{"id":"1811.01704","title":"ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks","created":"2018-11-05","cited_by_count":14},{"id":"2210.08502","title":"FIT: A Metric for Model Sensitivity","created":"2022-10-16","cited_by_count":11},{"id":"2010.08861","title":"Deep Learning in the Era of Edge Computing: Challenges and Opportunities","created":"2020-10-17","cited_by_count":10},{"id":"2010.01892","title":"Joint Pruning & Quantization for Extremely Sparse Neural Networks","created":"2020-10-05","cited_by_count":9},{"id":"2204.05639","title":"Neural Network Pruning by Cooperative Coevolution","created":"2022-04-12","cited_by_count":9},{"id":"2102.00160","title":"Deep Model Compression based on the Training History","created":"2021-01-30","cited_by_count":7},{"id":"2110.08271","title":"Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations","created":"2021-10-15","cited_by_count":7},{"id":"2203.02549","title":"Structured Pruning is All You Need for Pruning CNNs at Initialization","created":"2022-03-04","cited_by_count":7},{"id":"2008.08284","title":"Channel-wise Hessian Aware trace-Weighted Quantization of Neural Networks","created":"2020-08-19","cited_by_count":6},{"id":"2302.01382","title":"Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search","created":"2023-02-02","cited_by_count":3}],"next_cursor":null}