{"list":"other","total":73,"rows":[{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"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":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"2004.10568","title":"Up or Down? Adaptive Rounding for Post-Training Quantization","created":"2020-04-22","cited_by_count":621},{"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":"2102.05426","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","created":"2021-02-10","cited_by_count":479},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"id":"2001.00281","title":"ZeroQ: A Novel Zero Shot Quantization Framework","created":"2020-01-01","cited_by_count":269},{"id":"2004.02178","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","created":"2020-04-05","cited_by_count":226},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"2004.09576","title":"LSQ+: Improving low-bit quantization through learnable offsets and better initialization","created":"2020-04-20","cited_by_count":189},{"id":"1901.09504","title":"Improving Neural Network Quantization without Retraining using Outlier Channel Splitting","created":"2019-01-28","cited_by_count":151},{"id":"2004.07320","title":"Training with Quantization Noise for Extreme Model Compression","created":"2020-04-15","cited_by_count":145},{"id":"1511.06393","title":"Fixed Point Quantization of Deep Convolutional Networks","created":"2015-11-19","cited_by_count":143},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1907.08349","title":"Convergence of Edge Computing and Deep Learning: A Comprehensive Survey","created":"2019-07-19","cited_by_count":120},{"id":"2203.11086","title":"Overcoming Oscillations in Quantization-Aware Training","created":"2022-03-21","cited_by_count":119},{"id":"2008.05000","title":"Degree-Quant: Quantization-Aware Training for Graph Neural Networks","created":"2020-08-11","cited_by_count":96},{"id":"2005.07093","title":"Bayesian Bits: Unifying Quantization and Pruning","created":"2020-05-14","cited_by_count":94},{"id":"2006.10518","title":"Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming","created":"2020-06-14","cited_by_count":92},{"id":"1903.08066","title":"Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks","created":"2019-03-19","cited_by_count":90},{"id":"1908.00080","title":"Machine Learning at the Network Edge: A Survey","created":"2019-07-31","cited_by_count":84},{"id":"2002.03532","title":"Understanding and Improving Knowledge Distillation","created":"2020-02-10","cited_by_count":83},{"id":"2002.00104","title":"Post-Training Piecewise Linear Quantization for Deep Neural Networks","created":"2020-01-31","cited_by_count":79},{"id":"1909.00560","title":"Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence","created":"2019-09-02","cited_by_count":76},{"id":"1810.10090","title":"NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision","created":"2018-10-23","cited_by_count":68},{"id":"1908.06294","title":"Improved Techniques for Training Adaptive Deep Networks","created":"2019-08-17","cited_by_count":66},{"id":"2111.05754","title":"Prune Once for All: Sparse Pre-Trained Language Models","created":"2021-11-10","cited_by_count":66},{"id":"1612.00694","title":"ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA","created":"2016-12-01","cited_by_count":52},{"id":"1806.07840","title":"Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergy","created":"2018-06-20","cited_by_count":51},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46},{"id":"1902.01917","title":"Same, Same But Different - Recovering Neural Network Quantization Error Through Weight Factorization","created":"2019-02-05","cited_by_count":45},{"id":"1911.12491","title":"QKD: Quantization-aware Knowledge Distillation","created":"2019-11-28","cited_by_count":44},{"id":"1907.02745","title":"Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data","created":"2019-07-05","cited_by_count":39},{"id":"2102.11289","title":"Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference","created":"2021-02-22","cited_by_count":31},{"id":"2108.11898","title":"Supervised Compression for Resource-Constrained Edge Computing Systems","created":"2021-08-21","cited_by_count":31},{"id":"2108.13041","title":"Auto-Split: A General Framework of Collaborative Edge-Cloud AI","created":"2021-08-30","cited_by_count":30},{"id":"2309.14592","title":"Efficient Post-training Quantization with FP8 Formats","created":"2023-09-26","cited_by_count":29},{"id":"2007.15818","title":"Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks","created":"2020-07-31","cited_by_count":28},{"id":"2201.02693","title":"BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing","created":"2022-01-07","cited_by_count":28},{"id":"2010.04354","title":"Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search","created":"2020-10-09","cited_by_count":26},{"id":"2206.06501","title":"Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training","created":"2022-06-13","cited_by_count":26},{"id":"2009.14502","title":"Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks","created":"2020-09-30","cited_by_count":21},{"id":"2106.14681","title":"PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation","created":"2021-06-25","cited_by_count":21},{"id":"1810.05488","title":"Quantization for Rapid Deployment of Deep Neural Networks","created":"2018-10-12","cited_by_count":20},{"id":"1812.06426","title":"Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge","created":"2018-12-16","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":"2105.11010","title":"Post-Training Sparsity-Aware Quantization","created":"2021-05-23","cited_by_count":17},{"id":"2101.05938","title":"KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization","created":"2021-01-15","cited_by_count":15},{"id":"2203.08875","title":"SC2 Benchmark: Supervised Compression for Split Computing","created":"2022-03-16","cited_by_count":15},{"id":"2102.06365","title":"Dynamic Precision Analog Computing for Neural Networks","created":"2021-02-12","cited_by_count":12},{"id":"2102.06366","title":"Confounding Tradeoffs for Neural Network Quantization","created":"2021-02-12","cited_by_count":9},{"id":"2206.14322","title":"An Empirical Study of Challenges in Converting Deep Learning Models","created":"2022-06-28","cited_by_count":8},{"id":"2105.00591","title":"Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation","created":"2021-05-03","cited_by_count":6},{"id":"2208.09684","title":"Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks","created":"2022-08-20","cited_by_count":4},{"id":"2403.17154","title":"On the Impact of Black-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-03-25","cited_by_count":3},{"id":"2211.07715","title":"Fast DistilBERT on CPUs","created":"2022-10-27","cited_by_count":2},{"id":"2306.12185","title":"Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource","created":"2023-06-21","cited_by_count":2},{"id":"2210.17114","title":"QuaLA-MiniLM: a Quantized Length Adaptive MiniLM","created":"2022-10-31","cited_by_count":1}],"next_cursor":null}