{"list":"other","total":65,"rows":[{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"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":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"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":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163},{"id":"2006.10901","title":"Sparse GPU Kernels for Deep Learning","created":"2020-06-18","cited_by_count":141},{"id":"1805.08166","title":"Learning to Optimize Tensor Programs","created":"2018-05-21","cited_by_count":140},{"id":"1705.08665","title":"Bayesian Compression for Deep Learning","created":"2017-05-24","cited_by_count":116},{"id":"2007.00072","title":"Data Movement Is All You Need: A Case Study on Optimizing Transformers","created":"2020-06-30","cited_by_count":108},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106},{"id":"1911.09723","title":"Fast Sparse ConvNets","created":"2019-11-21","cited_by_count":86},{"id":"2008.05441","title":"Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network","created":"2020-08-12","cited_by_count":74},{"id":"2201.05125","title":"GradMax: Growing Neural Networks using Gradient Information","created":"2022-01-13","cited_by_count":66},{"id":"1906.10732","title":"The Difficulty of Training Sparse Neural Networks","created":"2019-06-25","cited_by_count":62},{"id":"1612.00694","title":"ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA","created":"2016-12-01","cited_by_count":52},{"id":"2207.04606","title":"SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning","created":"2022-07-11","cited_by_count":47},{"id":"2007.03179","title":"GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks","created":"2020-07-07","cited_by_count":42},{"id":"1901.09290","title":"PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration","created":"2019-01-26","cited_by_count":41},{"id":"1608.01409","title":"Faster CNNs with Direct Sparse Convolutions and Guided Pruning","created":"2016-08-04","cited_by_count":39},{"id":"2207.02852","title":"Machine Learning Model Sizes and the Parameter Gap","created":"2022-07-05","cited_by_count":39},{"id":"2008.11359","title":"FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems","created":"2020-08-26","cited_by_count":36},{"id":"1802.08021","title":"SparCML: High-Performance Sparse Communication for Machine Learning","created":"2018-02-22","cited_by_count":34},{"id":"2008.11849","title":"SparseRT: Accelerating Unstructured Sparsity on GPUs for Deep Learning Inference","created":"2020-08-26","cited_by_count":30},{"id":"2205.09702","title":"Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis","created":"2022-05-19","cited_by_count":29},{"id":"2007.00864","title":"Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights","created":"2020-07-02","cited_by_count":28},{"id":"1811.00206","title":"Balanced Sparsity for Efficient DNN Inference on GPU","created":"2018-11-01","cited_by_count":27},{"id":"1902.09701","title":"Learning Implicitly Recurrent CNNs Through Parameter Sharing","created":"2019-02-26","cited_by_count":27},{"id":"2003.06307","title":"Communication-Efficient Distributed Deep Learning: A Comprehensive Survey","created":"2020-03-10","cited_by_count":26},{"id":"2201.07598","title":"Near-Optimal Sparse Allreduce for Distributed Deep Learning","created":"2022-01-19","cited_by_count":23},{"id":"2209.06979","title":"Efficient Quantized Sparse Matrix Operations on Tensor Cores","created":"2022-09-14","cited_by_count":16},{"id":"2001.10710","title":"Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks","created":"2020-01-29","cited_by_count":15},{"id":"2006.10598","title":"Neural Parameter Allocation Search","created":"2020-06-18","cited_by_count":15},{"id":"2112.13896","title":"Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networks","created":"2021-12-27","cited_by_count":15},{"id":"1802.10280","title":"Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs","created":"2018-02-28","cited_by_count":11},{"id":"2202.04305","title":"Compiler Support for Sparse Tensor Computations in MLIR","created":"2022-02-09","cited_by_count":8},{"id":"1702.08597","title":"Enabling Sparse Winograd Convolution by Native Pruning","created":"2017-02-28","cited_by_count":6},{"id":"1809.02209","title":"ProdSumNet: reducing model parameters in deep neural networks via product-of-sums matrix decompositions","created":"2018-09-06","cited_by_count":5}],"next_cursor":null}