{"list":"other","total":85,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"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":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1907.10597","title":"Green AI","created":"2019-07-22","cited_by_count":627},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"2003.08271","title":"Pre-trained Models for Natural Language Processing: A Survey","created":"2020-03-18","cited_by_count":505},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"2002.05651","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","created":"2020-01-31","cited_by_count":249},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"1711.08393","title":"BlockDrop: Dynamic Inference Paths in Residual Networks","created":"2017-11-22","cited_by_count":189},{"id":"1909.09656","title":"Understanding and Robustifying Differentiable Architecture Search","created":"2019-09-20","cited_by_count":178},{"id":"2007.03051","title":"Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models","created":"2020-07-06","cited_by_count":169},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169},{"id":"1808.07233","title":"Neural Architecture Optimization","created":"2018-08-22","cited_by_count":167},{"id":"1909.00015","title":"Adaptively Sparse Transformers","created":"2019-08-30","cited_by_count":155},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154},{"id":"1711.11503","title":"Convolutional Networks with Adaptive Inference Graphs","created":"2017-11-30","cited_by_count":148},{"id":"2003.07326","title":"Resolution Adaptive Networks for Efficient Inference","created":"2020-03-16","cited_by_count":146},{"id":"2004.07320","title":"Training with Quantization Noise for Extreme Model Compression","created":"2020-04-15","cited_by_count":145},{"id":"1711.09224","title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions","created":"2017-11-25","cited_by_count":122},{"id":"1909.03341","title":"Neural Machine Translation with Byte-Level Subwords","created":"2019-09-07","cited_by_count":115},{"id":"2103.00823","title":"M6: A Chinese Multimodal Pretrainer","created":"2021-03-01","cited_by_count":91},{"id":"1705.06963","title":"A Survey of Neuromorphic Computing and Neural Networks in Hardware","created":"2017-05-19","cited_by_count":85},{"id":"2104.06022","title":"Lessons on Parameter Sharing across Layers in Transformers","created":"2021-04-13","cited_by_count":85},{"id":"1412.2007","title":"On Using Very Large Target Vocabulary for Neural Machine Translation","created":"2014-12-05","cited_by_count":80},{"id":"1808.07512","title":"SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation","created":"2018-08-22","cited_by_count":72},{"id":"1909.02107","title":"Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems","created":"2019-09-04","cited_by_count":68},{"id":"1611.01587","title":"A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks","created":"2016-11-05","cited_by_count":62},{"id":"2208.00406","title":"Eco2AI: carbon emissions tracking of machine learning models as the first step towards sustainable AI","created":"2022-07-31","cited_by_count":58},{"id":"1801.04380","title":"SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks","created":"2018-01-13","cited_by_count":55},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52},{"id":"1911.08354","title":"Energy Usage Reports: Environmental awareness as part of algorithmic accountability","created":"2019-11-19","cited_by_count":44},{"id":"1711.01068","title":"Compressing Word Embeddings via Deep Compositional Code Learning","created":"2017-11-03","cited_by_count":35},{"id":"1603.00810","title":"Character-based Neural Machine Translation","created":"2016-03-02","cited_by_count":33},{"id":"2007.04239","title":"A Survey on Transfer Learning in Natural Language Processing","created":"2020-05-31","cited_by_count":33},{"id":"1806.06950","title":"GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking","created":"2018-06-18","cited_by_count":32},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32},{"id":"2011.13635","title":"Progressively Stacking 2.0: A Multi-stage Layerwise Training Method for BERT Training Speedup","created":"2020-11-27","cited_by_count":31},{"id":"2011.14808","title":"Bringing AI To Edge: From Deep Learning's Perspective","created":"2020-11-25","cited_by_count":24},{"id":"1412.5474","title":"Flattened Convolutional Neural Networks for Feedforward Acceleration","created":"2014-12-17","cited_by_count":20},{"id":"1707.06990","title":"Memory-Efficient Implementation of DenseNets","created":"2017-07-21","cited_by_count":17},{"id":"2005.03566","title":"Noisy Differentiable Architecture Search","created":"2020-05-07","cited_by_count":16},{"id":"1512.04906","title":"Strategies for Training Large Vocabulary Neural Language Models","created":"2015-12-15","cited_by_count":14},{"id":"2012.08044","title":"Deep Bayesian Active Learning, A Brief Survey on Recent Advances","created":"2020-12-15","cited_by_count":12},{"id":"2107.02621","title":"Energy Consumption of Deep Generative Audio Models","created":"2021-07-06","cited_by_count":12},{"id":"1810.08854","title":"pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference","created":"2018-10-20","cited_by_count":10},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9},{"id":"1412.7479","title":"Deep Networks With Large Output Spaces","created":"2014-12-23","cited_by_count":7},{"id":"1506.04488","title":"Distilling Word Embeddings: An Encoding Approach","created":"2015-06-15","cited_by_count":7},{"id":"1802.03750","title":"FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy","created":"2018-02-11","cited_by_count":7},{"id":"2007.07610","title":"Green Algorithms: Quantifying the carbon footprint of computation","created":"2020-07-15","cited_by_count":7},{"id":"2109.06762","title":"Greenformer: Factorization Toolkit for Efficient Deep Neural Networks","created":"2021-09-14","cited_by_count":7},{"id":"2204.03855","title":"Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition","created":"2022-04-08","cited_by_count":7},{"id":"2103.16435","title":"EnergyVis: Interactively Tracking and Exploring Energy Consumption for ML Models","created":"2021-03-30","cited_by_count":4},{"id":"2109.04847","title":"Active learning for reducing labeling effort in text classification tasks","created":"2021-09-10","cited_by_count":4},{"id":"2108.13465","title":"Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision","created":"2021-08-30","cited_by_count":2}],"next_cursor":null}