{"list":"other","total":99,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"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":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"1811.08886","title":"HAQ: Hardware-Aware Automated Quantization with Mixed Precision","created":"2018-11-21","cited_by_count":443},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"2004.04037","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","created":"2020-04-08","cited_by_count":251},{"id":"1905.10083","title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing","created":"2019-05-24","cited_by_count":228},{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162},{"id":"1910.05316","title":"Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing","created":"2019-10-04","cited_by_count":152},{"id":"2112.06409","title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective","created":"2021-12-13","cited_by_count":116},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104},{"id":"2410.11845","title":"A Review on Edge Large Language Models: Design, Execution, and Applications","created":"2024-09-29","cited_by_count":100},{"id":"1702.04008","title":"Soft Weight-Sharing for Neural Network Compression","created":"2017-02-13","cited_by_count":99},{"id":"2111.12444","title":"Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications","created":"2021-11-24","cited_by_count":97},{"id":"2002.09668","title":"Communication-Efficient Edge AI: Algorithms and Systems","created":"2020-02-22","cited_by_count":96},{"id":"1910.14315","title":"BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems","created":"2019-10-31","cited_by_count":95},{"id":"1812.02858","title":"Wireless Network Intelligence at the Edge","created":"2018-12-07","cited_by_count":92},{"id":"1908.00080","title":"Machine Learning at the Network Edge: A Survey","created":"2019-07-31","cited_by_count":84},{"id":"1804.11238","title":"Privacy Preserving Machine Learning: Threats and Solutions","created":"2018-03-27","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":"2001.00138","title":"PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning","created":"2020-01-01","cited_by_count":76},{"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":"1911.00623","title":"On-Device Machine Learning: An Algorithms and Learning Theory Perspective","created":"2019-11-02","cited_by_count":63},{"id":"2108.04417","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","created":"2021-08-10","cited_by_count":58},{"id":"2004.09031","title":"Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification","created":"2020-04-20","cited_by_count":53},{"id":"2109.00574","title":"Active label cleaning for improved dataset quality under resource constraints","created":"2021-09-01","cited_by_count":44},{"id":"1510.01722","title":"Structured Transforms for Small-Footprint Deep Learning","created":"2015-10-06","cited_by_count":42},{"id":"1806.09228","title":"Deep $k$-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions","created":"2018-06-24","cited_by_count":33},{"id":"2007.08860","title":"FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks","created":"2020-07-17","cited_by_count":32},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32},{"id":"2207.06646","title":"DropNet: Reducing Neural Network Complexity via Iterative Pruning","created":"2022-07-14","cited_by_count":29},{"id":"2210.09603","title":"Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs","created":"2022-10-18","cited_by_count":28},{"id":"2112.01849","title":"Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition","created":"2021-10-08","cited_by_count":25},{"id":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","cited_by_count":25},{"id":"2312.00333","title":"Green Edge AI: A Contemporary Survey","created":"2023-12-01","cited_by_count":25},{"id":"2012.13113","title":"FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training","created":"2020-12-24","cited_by_count":23},{"id":"1906.00400","title":"Mobile Edge Intelligence and Computing for the Internet of Vehicles","created":"2019-06-02","cited_by_count":22},{"id":"2205.14942","title":"Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles","created":"2022-05-30","cited_by_count":22},{"id":"2007.06631","title":"T-Basis: a Compact Representation for Neural Networks","created":"2020-07-13","cited_by_count":21},{"id":"2009.14502","title":"Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks","created":"2020-09-30","cited_by_count":21},{"id":"2202.11317","title":"The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devices","created":"2022-02-23","cited_by_count":21},{"id":"2204.11091","title":"On-Device Next-Item Recommendation with Self-Supervised Knowledge Distillation","created":"2022-04-23","cited_by_count":21},{"id":"2310.04621","title":"Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences","created":"2023-10-06","cited_by_count":21},{"id":"2311.10986","title":"EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge","created":"2023-11-18","cited_by_count":21},{"id":"1903.05898","title":"High-Throughput CNN Inference on Embedded ARM big.LITTLE Multi-Core Processors","created":"2019-03-14","cited_by_count":19},{"id":"2012.13600","title":"EdgeDRNN: Recurrent Neural Network Accelerator for Edge Inference","created":"2020-12-25","cited_by_count":19},{"id":"2005.05085","title":"Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices","created":"2020-05-07","cited_by_count":17},{"id":"2312.14229","title":"Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI","created":"2023-12-21","cited_by_count":17},{"id":"2110.00337","title":"PhiNets: a scalable backbone for low-power AI at the edge","created":"2021-10-01","cited_by_count":16},{"id":"2205.11845","title":"CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature Sharing","created":"2022-05-24","cited_by_count":15},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14},{"id":"2006.07900","title":"ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification","created":"2020-06-14","cited_by_count":12},{"id":"2004.13139","title":"A Generic Network Compression Framework for Sequential Recommender Systems","created":"2020-04-21","cited_by_count":10},{"id":"2007.02202","title":"A Survey on Applications of Artificial Intelligence in Fighting Against COVID-19","created":"2020-07-04","cited_by_count":10},{"id":"1701.04507","title":"Continuous Authentication for Voice Assistants","created":"2017-01-17","cited_by_count":9},{"id":"1911.06633","title":"HealthFog: An Ensemble Deep Learning based Smart Healthcare System for Automatic Diagnosis of Heart Diseases in Integrated IoT and Fog Computing Environments","created":"2019-11-15","cited_by_count":9},{"id":"2001.01043","title":"SurveilEdge: Real-time Video Query based on Collaborative Cloud-Edge Deep Learning","created":"2020-01-04","cited_by_count":9},{"id":"2008.03252","title":"A Survey on Security and Privacy Issues in Edge Computing-Assisted Internet of Things","created":"2020-08-05","cited_by_count":9},{"id":"2011.12289","title":"MicroNet: Towards Image Recognition with Extremely Low FLOPs","created":"2020-11-24","cited_by_count":9},{"id":"2011.05708","title":"Optimizing AI Service Placement and Resource Allocation in Mobile Edge Intelligence Systems","created":"2020-11-11","cited_by_count":8},{"id":"2103.12144","title":"Edge Intelligence for Empowering IoT-based Healthcare Systems","created":"2021-03-22","cited_by_count":8},{"id":"2205.08119","title":"ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks","created":"2022-05-17","cited_by_count":8},{"id":"1906.06847","title":"Structured Pruning of Recurrent Neural Networks through Neuron Selection","created":"2019-06-17","cited_by_count":7},{"id":"2010.01343","title":"A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition","created":"2020-10-03","cited_by_count":7},{"id":"2303.15540","title":"Intel TDX Demystified: A Top-Down Approach","created":"2023-03-27","cited_by_count":7},{"id":"2004.07116","title":"Q-CapsNets: A Specialized Framework for Quantizing Capsule Networks","created":"2020-04-15","cited_by_count":6},{"id":"2106.14928","title":"Caching and Computation Offloading in High Altitude Platform Station (HAPS) Assisted Intelligent Transportation Systems","created":"2021-06-28","cited_by_count":6},{"id":"2201.07312","title":"Model-driven Cluster Resource Management for AI Workloads in Edge Clouds","created":"2022-01-18","cited_by_count":6},{"id":"2209.13443","title":"Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs","created":"2022-09-27","cited_by_count":6},{"id":"2009.04247","title":"Binarized Neural Architecture Search for Efficient Object Recognition","created":"2020-09-08","cited_by_count":5},{"id":"2011.08442","title":"Edge Intelligence for Energy-efficient Computation Offloading and Resource Allocation in 5G Beyond","created":"2020-11-17","cited_by_count":4},{"id":"2304.11374","title":"Towards Carbon-Neutral Edge Computing: Greening Edge AI by Harnessing Spot and Future Carbon Markets","created":"2023-04-22","cited_by_count":4},{"id":"1711.09553","title":"Accessible Melanoma Detection using Smartphones and Mobile Image Analysis","created":"2017-11-27","cited_by_count":3},{"id":"2010.16165","title":"Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices","created":"2020-10-30","cited_by_count":3},{"id":"2103.13581","title":"EfficientTDNN: Efficient Architecture Search for Speaker Recognition","created":"2021-03-25","cited_by_count":3},{"id":"1901.02126","title":"Smart-Edge-CoCaCo: AI-Enabled Smart Edge with Joint Computation, Caching, and Communication in Heterogeneous IoT","created":"2019-01-08","cited_by_count":2},{"id":"2101.06371","title":"NNStreamer: Efficient and Agile Development of On-Device AI Systems","created":"2021-01-16","cited_by_count":2},{"id":"2109.06440","title":"Complexity-aware Adaptive Training and Inference for Edge-Cloud Distributed AI Systems","created":"2021-09-14","cited_by_count":2},{"id":"1806.01248","title":"Dynamically Hierarchy Revolution: DirNet for Compressing Recurrent Neural Network on Mobile Devices","created":"2018-06-04","cited_by_count":1},{"id":"2201.06026","title":"Toward Among-Device AI from On-Device AI with Stream Pipelines","created":"2022-01-16","cited_by_count":1}],"next_cursor":null}