{"list":"other","total":64,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"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":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"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":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"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":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"1907.05737","title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","created":"2019-07-12","cited_by_count":265},{"id":"1803.08664","title":"Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network","created":"2018-03-23","cited_by_count":264},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1904.12760","title":"Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation","created":"2019-04-29","cited_by_count":230},{"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":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","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":"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":"1804.03294","title":"A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers","created":"2018-04-10","cited_by_count":120},{"id":"1909.08174","title":"Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks","created":"2019-09-18","cited_by_count":118},{"id":"2005.07093","title":"Bayesian Bits: Unifying Quantization and Pruning","created":"2020-05-14","cited_by_count":94},{"id":"2007.02491","title":"EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning","created":"2020-07-06","cited_by_count":80},{"id":"2003.05643","title":"Highly Efficient Salient Object Detection with 100K Parameters","created":"2020-03-12","cited_by_count":79},{"id":"2007.03938","title":"Operation-Aware Soft Channel Pruning using Differentiable Masks","created":"2020-07-08","cited_by_count":74},{"id":"2003.08935","title":"Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression","created":"2020-03-19","cited_by_count":72},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70},{"id":"2301.11300","title":"ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients","created":"2023-01-26","cited_by_count":58},{"id":"1908.09979","title":"DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures","created":"2019-08-27","cited_by_count":56},{"id":"2103.10559","title":"CDFI: Compression-Driven Network Design for Frame Interpolation","created":"2021-03-18","cited_by_count":56},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50},{"id":"2009.14410","title":"Pruning Filter in Filter","created":"2020-09-30","cited_by_count":47},{"id":"2203.14186","title":"RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution","created":"2022-03-27","cited_by_count":44},{"id":"1812.04368","title":"Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression","created":"2018-12-11","cited_by_count":40},{"id":"1912.10952","title":"Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild","created":"2019-12-23","cited_by_count":40},{"id":"2310.18356","title":"LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery","created":"2023-10-24","cited_by_count":38},{"id":"2010.06176","title":"ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding","created":"2020-10-13","cited_by_count":36},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32},{"id":"1812.00353","title":"Accelerate CNN via Recursive Bayesian Pruning","created":"2018-12-02","cited_by_count":27},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26},{"id":"2004.03639","title":"Orthant Based Proximal Stochastic Gradient Method for $\\ell_1$-Regularized Optimization","created":"2020-04-07","cited_by_count":20},{"id":"2102.03869","title":"Structured Sparsity Inducing Adaptive Optimizers for Deep Learning","created":"2021-02-07","cited_by_count":17},{"id":"2011.04868","title":"Neural Network Compression Via Sparse Optimization","created":"2020-11-10","cited_by_count":13},{"id":"1909.01051","title":"MANAS: Multi-Agent Neural Architecture Search","created":"2019-09-03","cited_by_count":10},{"id":"1602.07018","title":"A Reduced-Space Algorithm for Minimizing $\\ell_1$-Regularized Convex Functions","created":"2016-02-23","cited_by_count":7},{"id":"2001.05887","title":"MixPath: A Unified Approach for One-shot Neural Architecture Search","created":"2020-01-16","cited_by_count":7},{"id":"2009.12078","title":"Half-Space Proximal Stochastic Gradient Method for Group-Sparsity Regularized Problem","created":"2020-09-25","cited_by_count":7},{"id":"2209.04551","title":"Sparsity-guided Network Design for Frame Interpolation","created":"2022-09-09","cited_by_count":6},{"id":"2103.11833","title":"AutoSpace: Neural Architecture Search with Less Human Interference","created":"2021-03-22","cited_by_count":5},{"id":"2311.14307","title":"Cosine Similarity Knowledge Distillation for Individual Class Information Transfer","created":"2023-11-24","cited_by_count":5},{"id":"2107.13186","title":"AutoML Meets Time Series Regression Design and Analysis of the AutoSeries Challenge","created":"2021-07-28","cited_by_count":2}],"next_cursor":null}