{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"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":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"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":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"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":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"1902.07638","title":"Random Search and Reproducibility for Neural Architecture Search","created":"2019-02-20","cited_by_count":254},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"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":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177},{"id":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"1804.03230","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","created":"2018-04-09","cited_by_count":147},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"id":"2004.03844","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","created":"2020-04-08","cited_by_count":118},{"id":"1711.06798","title":"MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks","created":"2017-11-18","cited_by_count":94},{"id":"2005.07093","title":"Bayesian Bits: Unifying Quantization and Pruning","created":"2020-05-14","cited_by_count":94},{"id":"2008.06120","title":"Can weight sharing outperform random architecture search? An investigation with TuNAS","created":"2020-08-13","cited_by_count":68},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61},{"id":"2110.06554","title":"Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization","created":"2021-10-13","cited_by_count":61},{"id":"1908.09979","title":"DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures","created":"2019-08-27","cited_by_count":56},{"id":"1912.09640","title":"AtomNAS: Fine-Grained End-to-End Neural Architecture Search","created":"2019-12-20","cited_by_count":40},{"id":"2206.01198","title":"Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization","created":"2022-06-02","cited_by_count":32},{"id":"1812.02402","title":"Trained Rank Pruning for Efficient Deep Neural Networks","created":"2018-12-06","cited_by_count":23},{"id":"1910.11609","title":"Fast Hardware-Aware Neural Architecture Search","created":"2019-10-25","cited_by_count":23},{"id":"2010.01791","title":"Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior","created":"2020-10-05","cited_by_count":23},{"id":"2104.12766","title":"HAO: Hardware-aware neural Architecture Optimization for Efficient Inference","created":"2021-04-26","cited_by_count":16},{"id":"1812.08852","title":"A Scale Invariant Approach for Sparse Signal Recovery","created":"2018-12-20","cited_by_count":13},{"id":"2008.08178","title":"Discovering Multi-Hardware Mobile Models via Architecture Search","created":"2020-08-18","cited_by_count":12},{"id":"2110.10811","title":"HALP: Hardware-Aware Latency Pruning","created":"2021-10-20","cited_by_count":8},{"id":"1604.02594","title":"Learning Compact Recurrent Neural Networks","created":"2016-04-09","cited_by_count":6},{"id":"2006.09581","title":"Fine-Grained Stochastic Architecture Search","created":"2020-06-17","cited_by_count":3}],"next_cursor":null}