{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"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":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"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":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1902.08153","title":"Learned Step Size Quantization","created":"2019-02-21","cited_by_count":628},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1905.03696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","created":"2019-04-29","cited_by_count":402},{"id":"1909.05840","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","created":"2019-09-12","cited_by_count":359},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"1807.10029","title":"LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks","created":"2018-07-26","cited_by_count":274},{"id":"1911.03852","title":"HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks","created":"2019-11-10","cited_by_count":261},{"id":"2101.01321","title":"I-BERT: Integer-only BERT Quantization","created":"2021-01-05","cited_by_count":255},{"id":"1908.05033","title":"Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks","created":"2019-08-14","cited_by_count":238},{"id":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"id":"2003.03488","title":"ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions","created":"2020-03-07","cited_by_count":184},{"id":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"1812.08011","title":"Training Deep Neural Networks with 8-bit Floating Point Numbers","created":"2018-12-19","cited_by_count":164},{"id":"1901.09504","title":"Improving Neural Network Quantization without Retraining using Outlier Channel Splitting","created":"2019-01-28","cited_by_count":151},{"id":"2009.12812","title":"TernaryBERT: Distillation-aware Ultra-low Bit BERT","created":"2020-09-27","cited_by_count":148},{"id":"1805.11046","title":"Scalable Methods for 8-bit Training of Neural Networks","created":"2018-05-25","cited_by_count":142},{"id":"2002.00293","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","created":"2020-02-02","cited_by_count":131},{"id":"1802.04680","title":"Training and Inference with Integers in Deep Neural Networks","created":"2018-02-13","cited_by_count":86},{"id":"1912.12607","title":"Towards Unified INT8 Training for Convolutional Neural Network","created":"2019-12-29","cited_by_count":79},{"id":"2010.14298","title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","created":"2020-10-27","cited_by_count":51},{"id":"2106.11309","title":"How Do Adam and Training Strategies Help BNNs Optimization?","created":"2021-06-21","cited_by_count":46},{"id":"1804.01526","title":"Training DNNs with Hybrid Block Floating Point","created":"2018-04-04","cited_by_count":40},{"id":"1909.02384","title":"Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers","created":"2019-09-05","cited_by_count":33},{"id":"1805.08079","title":"Faster Neural Network Training with Approximate Tensor Operations","created":"2018-05-21","cited_by_count":14},{"id":"2203.13483","title":"MKQ-BERT: Quantized BERT with 4-bits Weights and Activations","created":"2022-03-25","cited_by_count":10},{"id":"1908.02386","title":"Cheetah: Mixed Low-Precision Hardware & Software Co-Design Framework for DNNs on the Edge","created":"2019-08-06","cited_by_count":8},{"id":"2210.07171","title":"SQuAT: Sharpness- and Quantization-Aware Training for BERT","created":"2022-10-13","cited_by_count":7},{"id":"1907.13216","title":"Deep Learning Training on the Edge with Low-Precision Posits","created":"2019-07-30","cited_by_count":4},{"id":"1911.00361","title":"Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers","created":"2019-11-01","cited_by_count":3}],"next_cursor":null}