{"list":"other","total":52,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"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":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"2012.09852","title":"SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning","created":"2020-12-17","cited_by_count":234},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"1911.02972","title":"Blockwise Self-Attention for Long Document Understanding","created":"2019-11-07","cited_by_count":159},{"id":"1909.00015","title":"Adaptively Sparse Transformers","created":"2019-08-30","cited_by_count":155},{"id":"1708.04485","title":"SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks","created":"2017-05-23","cited_by_count":135},{"id":"1712.01507","title":"Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks","created":"2017-12-05","cited_by_count":109},{"id":"2005.03842","title":"GOBO: Quantizing Attention-Based NLP Models for Low Latency and Energy Efficient Inference","created":"2020-05-08","cited_by_count":106},{"id":"2002.10941","title":"A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation","created":"2020-02-22","cited_by_count":101},{"id":"1611.06694","title":"Training Sparse Neural Networks","created":"2016-11-21","cited_by_count":73},{"id":"2011.14203","title":"EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference","created":"2020-11-28","cited_by_count":70},{"id":"1912.11637","title":"Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection","created":"2019-12-25","cited_by_count":62},{"id":"2103.09301","title":"Softermax: Hardware/Software Co-Design of an Efficient Softmax for Transformers","created":"2021-03-16","cited_by_count":54},{"id":"2105.11618","title":"TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference","created":"2021-05-25","cited_by_count":40},{"id":"2102.10423","title":"An Evaluation of Edge TPU Accelerators for Convolutional Neural Networks","created":"2021-02-20","cited_by_count":39},{"id":"1911.04070","title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","created":"2019-11-11","cited_by_count":38},{"id":"1610.06920","title":"Bit-pragmatic Deep Neural Network Computing","created":"2016-10-20","cited_by_count":32},{"id":"1805.03718","title":"Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks","created":"2018-05-09","cited_by_count":32},{"id":"1709.05027","title":"Learning Intrinsic Sparse Structures within Long Short-Term Memory","created":"2017-09-15","cited_by_count":18},{"id":"2003.00075","title":"Learned Threshold Pruning","created":"2020-02-28","cited_by_count":17},{"id":"1706.07853","title":"Loom: Exploiting Weight and Activation Precisions to Accelerate Convolutional Neural Networks","created":"2017-06-23","cited_by_count":12},{"id":"1906.11915","title":"Mixed-Signal Charge-Domain Acceleration of Deep Neural networks through Interleaved Bit-Partitioned Arithmetic","created":"2019-06-27","cited_by_count":6},{"id":"1909.07636","title":"Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks","created":"2019-09-17","cited_by_count":6},{"id":"2002.04971","title":"FastWave: Accelerating Autoregressive Convolutional Neural Networks on FPGA","created":"2020-02-09","cited_by_count":4},{"id":"2004.05333","title":"Bit-Parallel Vector Composability for Neural Acceleration","created":"2020-04-11","cited_by_count":4}],"next_cursor":null}