{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"id":"2010.02803","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","created":"2020-10-06","cited_by_count":453},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1710.09282","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","created":"2017-10-23","cited_by_count":301},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"id":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"2004.03333","title":"Binary Neural Networks: A Survey","created":"2020-03-31","cited_by_count":190},{"id":"2003.03488","title":"ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions","created":"2020-03-07","cited_by_count":184},{"id":"1909.10788","title":"Forward and Backward Information Retention for Accurate Binary Neural Networks","created":"2019-09-24","cited_by_count":169},{"id":"2206.15472","title":"On-Device Training Under 256KB Memory","created":"2022-06-30","cited_by_count":160},{"id":"1511.06393","title":"Fixed Point Quantization of Deep Convolutional Networks","created":"2015-11-19","cited_by_count":143},{"id":"2003.11535","title":"Training Binary Neural Networks with Real-to-Binary Convolutions","created":"2020-03-25","cited_by_count":112},{"id":"2110.15352","title":"MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning","created":"2021-10-28","cited_by_count":89},{"id":"1711.00205","title":"Towards Effective Low-bitwidth Convolutional Neural Networks","created":"2017-11-01","cited_by_count":78},{"id":"2103.05127","title":"Model Complexity of Deep Learning: A Survey","created":"2021-03-08","cited_by_count":65},{"id":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","cited_by_count":55},{"id":"2103.12369","title":"ReCU: Reviving the Dead Weights in Binary Neural Networks","created":"2021-03-23","cited_by_count":52},{"id":"2103.00841","title":"Learning Frequency Domain Approximation for Binary Neural Networks","created":"2021-03-01","cited_by_count":38},{"id":"1905.13082","title":"Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollers","created":"2019-05-30","cited_by_count":33},{"id":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22},{"id":"2009.04126","title":"FleXOR: Trainable Fractional Quantization","created":"2020-09-09","cited_by_count":9},{"id":"2110.09195","title":"Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks","created":"2021-10-18","cited_by_count":8},{"id":"2308.04637","title":"Sparse Binary Transformers for Multivariate Time Series Modeling","created":"2023-08-09","cited_by_count":8},{"id":"2002.12520","title":"Utilizing Network Properties to Detect Erroneous Inputs","created":"2020-02-28","cited_by_count":7},{"id":"2010.02778","title":"Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters","created":"2020-10-06","cited_by_count":5},{"id":"2303.14470","title":"Compacting Binary Neural Networks by Sparse Kernel Selection","created":"2023-03-25","cited_by_count":3},{"id":"2303.15953","title":"Randomly Initialized Subnetworks with Iterative Weight Recycling","created":"2023-03-28","cited_by_count":3},{"id":"2311.04818","title":"Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignment","created":"2023-11-08","cited_by_count":1}],"next_cursor":null}