{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"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":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"1909.09577","title":"NeMo: a toolkit for building AI applications using Neural Modules","created":"2019-09-14","cited_by_count":235},{"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":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"id":"1512.01274","title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems","created":"2015-12-03","cited_by_count":195},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131},{"id":"2006.07253","title":"Dynamic Model Pruning with Feedback","created":"2020-06-12","cited_by_count":125},{"id":"2102.01547","title":"WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit","created":"2021-02-02","cited_by_count":125},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122},{"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":"2012.09243","title":"Neural Pruning via Growing Regularization","created":"2020-12-16","cited_by_count":97},{"id":"1906.06307","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","created":"2019-06-14","cited_by_count":96},{"id":"2104.03438","title":"Convolutional Neural Network Pruning with Structural Redundancy Reduction","created":"2021-04-08","cited_by_count":73},{"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":"2006.09081","title":"Progressive Skeletonization: Trimming more fat from a network at initialization","created":"2020-06-16","cited_by_count":64},{"id":"2002.04809","title":"Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning","created":"2020-02-12","cited_by_count":61},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32},{"id":"2104.02244","title":"Content-Aware GAN Compression","created":"2021-04-06","cited_by_count":28},{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25},{"id":"2105.12971","title":"Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation","created":"2021-05-27","cited_by_count":23},{"id":"2004.03639","title":"Orthant Based Proximal Stochastic Gradient Method for $\\ell_1$-Regularized Optimization","created":"2020-04-07","cited_by_count":20},{"id":"1905.10138","title":"Structured Compression by Weight Encryption for Unstructured Pruning and Quantization","created":"2019-05-24","cited_by_count":16},{"id":"2006.09358","title":"Directional Pruning of Deep Neural Networks","created":"2020-06-16","cited_by_count":16},{"id":"2301.05219","title":"Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning","created":"2023-01-12","cited_by_count":16},{"id":"2011.04868","title":"Neural Network Compression Via Sparse Optimization","created":"2020-11-10","cited_by_count":13},{"id":"2108.11033","title":"GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity","created":"2021-08-25","cited_by_count":10},{"id":"2403.18955","title":"Structurally Prune Anything: Any Architecture, Any Framework, Any Time","created":"2024-03-03","cited_by_count":8},{"id":"2107.08815","title":"Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data","created":"2021-07-16","cited_by_count":1}],"next_cursor":null}