{"list":"other","total":54,"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":"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":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"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":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"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":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"1705.08741","title":"Train longer, generalize better: closing the generalization gap in large batch training of neural networks","created":"2017-05-24","cited_by_count":279},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245},{"id":"2010.13154","title":"Attention is All You Need in Speech Separation","created":"2020-10-25","cited_by_count":185},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141},{"id":"2005.14187","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","created":"2020-05-28","cited_by_count":136},{"id":"1708.04485","title":"SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks","created":"2017-05-23","cited_by_count":135},{"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":"2201.00044","title":"Transformer Embeddings of Irregularly Spaced Events and Their Participants","created":"2021-12-31","cited_by_count":93},{"id":"1802.04730","title":"Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions","created":"2018-02-13","cited_by_count":85},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79},{"id":"2204.12997","title":"DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers","created":"2022-04-27","cited_by_count":65},{"id":"1403.1687","title":"Rigid-Motion Scattering for Texture Classification","created":"2014-03-07","cited_by_count":52},{"id":"1612.01543","title":"Towards the Limit of Network Quantization","created":"2016-12-05","cited_by_count":50},{"id":"2209.10797","title":"DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation","created":"2022-09-22","cited_by_count":48},{"id":"2210.09573","title":"ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design","created":"2022-10-18","cited_by_count":41},{"id":"1909.13639","title":"NeuroVectorizer: End-to-End Vectorization with Deep Reinforcement Learning","created":"2019-09-20","cited_by_count":37},{"id":"1910.10485","title":"Fully Quantized Transformer for Machine Translation","created":"2019-10-17","cited_by_count":36},{"id":"1809.04070","title":"Interstellar: Using Halide's Scheduling Language to Analyze DNN Accelerators","created":"2018-09-10","cited_by_count":34},{"id":"2107.13686","title":"AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models","created":"2021-07-29","cited_by_count":31},{"id":"1809.02697","title":"Optimizing CNN Model Inference on CPUs","created":"2018-09-07","cited_by_count":29},{"id":"1908.05858","title":"daBNN: A Super Fast Inference Framework for Binary Neural Networks on ARM devices","created":"2019-08-16","cited_by_count":27},{"id":"2003.02369","title":"Ordering Chaos: Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices","created":"2020-03-04","cited_by_count":27},{"id":"2110.04035","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2021-10-08","cited_by_count":23},{"id":"1802.06367","title":"Efficient Sparse-Winograd Convolutional Neural Networks","created":"2018-02-18","cited_by_count":20},{"id":"2009.10976","title":"Procrustes: a Dataflow and Accelerator for Sparse Deep Neural Network Training","created":"2020-09-23","cited_by_count":18},{"id":"2202.13393","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","created":"2022-02-27","cited_by_count":17},{"id":"2009.07453","title":"Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation","created":"2020-09-16","cited_by_count":14},{"id":"2108.02598","title":"Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification","created":"2021-08-05","cited_by_count":14},{"id":"2002.10711","title":"Searching for Winograd-aware Quantized Networks","created":"2020-02-25","cited_by_count":11},{"id":"2206.14550","title":"SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences","created":"2022-06-29","cited_by_count":10},{"id":"2201.10369","title":"Winograd Convolution for Deep Neural Networks: Efficient Point Selection","created":"2022-01-25","cited_by_count":8},{"id":"2102.06621","title":"Optimizing Inference Performance of Transformers on CPUs","created":"2021-02-12","cited_by_count":7},{"id":"1901.01965","title":"Efficient Winograd Convolution via Integer Arithmetic","created":"2019-01-07","cited_by_count":6},{"id":"1903.01521","title":"Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs","created":"2019-03-04","cited_by_count":5},{"id":"1804.08733","title":"goSLP: Globally Optimized Superword Level Parallelism Framework","created":"2018-04-23","cited_by_count":3},{"id":"2306.00229","title":"Minotaur: A SIMD-Oriented Synthesizing Superoptimizer","created":"2023-05-31","cited_by_count":2}],"next_cursor":null}