{"list":"other","total":52,"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":"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"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":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"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":"1911.03852","title":"HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks","created":"2019-11-10","cited_by_count":261},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"1903.09291","title":"Towards Optimal Structured CNN Pruning via Generative Adversarial Learning","created":"2019-03-22","cited_by_count":146},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122},{"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":"1705.08665","title":"Bayesian Compression for Deep Learning","created":"2017-05-24","cited_by_count":116},{"id":"2006.08509","title":"APQ: Joint Search for Network Architecture, Pruning and Quantization Policy","created":"2020-06-15","cited_by_count":99},{"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":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70},{"id":"1802.10399","title":"Compressing Neural Networks using the Variational Information Bottleneck","created":"2018-02-28","cited_by_count":59},{"id":"1908.09979","title":"DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures","created":"2019-08-27","cited_by_count":56},{"id":"2305.18403","title":"LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning","created":"2023-05-28","cited_by_count":53},{"id":"1904.04421","title":"FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge","created":"2019-04-09","cited_by_count":48},{"id":"2009.14410","title":"Pruning Filter in Filter","created":"2020-09-30","cited_by_count":47},{"id":"2007.10463","title":"Differentiable Joint Pruning and Quantization for Hardware Efficiency","created":"2020-07-20","cited_by_count":46},{"id":"1812.04368","title":"Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression","created":"2018-12-11","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":"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":"2207.10345","title":"CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution","created":"2022-07-21","cited_by_count":27},{"id":"2004.03639","title":"Orthant Based Proximal Stochastic Gradient Method for $\\ell_1$-Regularized Optimization","created":"2020-04-07","cited_by_count":20},{"id":"2205.11141","title":"OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization","created":"2022-05-23","cited_by_count":19},{"id":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19},{"id":"1905.11452","title":"Mixed Precision DNNs: All you need is a good parametrization","created":"2019-05-27","cited_by_count":18},{"id":"1811.01907","title":"A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM","created":"2018-11-05","cited_by_count":10},{"id":"2312.15322","title":"Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization","created":"2023-12-23","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":"2101.04935","title":"Single-path Bit Sharing for Automatic Loss-aware Model Compression","created":"2021-01-13","cited_by_count":6},{"id":"2312.09411","title":"OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators","created":"2023-12-15","cited_by_count":6},{"id":"2409.09085","title":"HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning","created":"2024-09-11","cited_by_count":4}],"next_cursor":null}