{"total":74,"rows":[{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2102.13451","title":"FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout","created":"2021-02-26","cited_by_count":192,"area":null},{"id":"2105.11367","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","created":"2021-05-24","cited_by_count":136,"area":null},{"id":"2211.01549","title":"Client Selection in Federated Learning: Principles, Challenges, and Opportunities","created":"2022-11-03","cited_by_count":62,"area":null},{"id":"2101.02833","title":"Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition","created":"2021-01-08","cited_by_count":48,"area":null},{"id":"2105.07809","title":"Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":34,"area":null},{"id":"2105.07825","title":"Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":34,"area":null},{"id":"2504.03360","title":"Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency","created":"2025-04-04","cited_by_count":34,"area":null},{"id":"2105.10288","title":"Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices","created":"2021-05-21","cited_by_count":30,"area":null},{"id":"2304.06947","title":"TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training","created":"2023-04-14","cited_by_count":27,"area":null},{"id":"2109.13963","title":"Smart at what cost? Characterising Mobile Deep Neural Networks in the wild","created":"2021-09-28","cited_by_count":25,"area":null},{"id":"2105.09750","title":"Anchor-based Plain Net for Mobile Image Super-Resolution","created":"2021-05-20","cited_by_count":24,"area":null},{"id":"2105.08630","title":"Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":19,"area":null},{"id":"2105.08826","title":"Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":19,"area":null},{"id":"2102.01393","title":"It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation","created":"2021-02-02","cited_by_count":18,"area":null},{"id":"2104.09949","title":"DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device","created":"2021-04-20","cited_by_count":18,"area":null},{"id":"2106.03527","title":"Multi-Exit Semantic Segmentation Networks","created":"2021-06-07","cited_by_count":18,"area":null},{"id":"2310.18329","title":"Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices","created":"2023-10-19","cited_by_count":17,"area":null},{"id":"2211.05910","title":"Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report","created":"2022-11-07","cited_by_count":16,"area":null},{"id":"2105.08629","title":"Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":15,"area":null},{"id":"2106.09216","title":"Layer Pruning on Demand with Intermediate CTC","created":"2021-06-17","cited_by_count":13,"area":null},{"id":"2211.03885","title":"Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report","created":"2022-11-07","cited_by_count":13,"area":null},{"id":"2211.06770","title":"MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learning","created":"2022-11-08","cited_by_count":13,"area":null},{"id":"2402.00033","title":"LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition","created":"2024-01-08","cited_by_count":13,"area":null},{"id":"2202.06512","title":"Benchmarking of DL Libraries and Models on Mobile Devices","created":"2022-02-14","cited_by_count":12,"area":null},{"id":"2207.07958","title":"FastML Science Benchmarks: Accelerating Real-Time Scientific Edge Machine Learning","created":"2022-07-16","cited_by_count":12,"area":null},{"id":"2105.08819","title":"Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report","created":"2021-05-17","cited_by_count":10,"area":null},{"id":"2305.03888","title":"Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning","created":"2023-05-06","cited_by_count":10,"area":null},{"id":"2410.03613","title":"Understanding Large Language Models in Your Pockets: Performance Study on COTS Mobile Devices","created":"2024-10-04","cited_by_count":10,"area":null},{"id":"2104.08094","title":"Personalized Semi-Supervised Federated Learning for Human Activity Recognition","created":"2021-04-15","cited_by_count":9,"area":null},{"id":"2106.03727","title":"Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions","created":"2021-06-07","cited_by_count":9,"area":null},{"id":"2209.08907","title":"Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning","created":"2022-09-19","cited_by_count":9,"area":null},{"id":"2111.01203","title":"One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search","created":"2021-11-01","cited_by_count":8,"area":null},{"id":"2201.03789","title":"Partial Model Averaging in Federated Learning: Performance Guarantees and Benefits","created":"2022-01-11","cited_by_count":8,"area":null},{"id":"2106.04723","title":"OODIn: An Optimised On-Device Inference Framework for Heterogeneous Mobile Devices","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2209.15529","title":"TT-NF: Tensor Train Neural Fields","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2211.06263","title":"PyNet-V2 Mobile: Efficient On-Device Photo Processing With Neural Networks","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2208.11609","title":"Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution","created":"2022-08-24","cited_by_count":6,"area":null},{"id":"2310.11096","title":"Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2308.08137","title":"SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device","created":"2023-08-16","cited_by_count":5,"area":null},{"id":"2206.11239","title":"FedorAS: Federated Architecture Search under system heterogeneity","created":"2022-06-22","cited_by_count":4,"area":null},{"id":"2211.04470","title":"Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report","created":"2022-11-07","cited_by_count":4,"area":null},{"id":"2303.01509","title":"EPAM: A Predictive Energy Model for Mobile AI","created":"2023-03-02","cited_by_count":4,"area":null},{"id":"2208.11608","title":"Sliding Window Recurrent Network for Efficient Video Super-Resolution","created":"2022-08-24","cited_by_count":3,"area":null},{"id":"2208.12343","title":"Bokeh-Loss GAN: Multi-Stage Adversarial Training for Realistic Edge-Aware Bokeh","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2211.05256","title":"Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report","created":"2022-11-07","cited_by_count":3,"area":null},{"id":"2106.15021","title":"How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2208.00485","title":"Adaptive Edge Offloading for Image Classification Under Rate Limit","created":"2022-07-31","cited_by_count":2,"area":null},{"id":"2211.06769","title":"Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report","created":"2022-11-07","cited_by_count":2,"area":null},{"id":"2105.02613","title":"Challenges and Obstacles Towards Deploying Deep Learning Models on Mobile Devices","created":"2021-05-06","cited_by_count":1,"area":null},{"id":"2105.07869","title":"Fast and Accurate Camera Scene Detection on Smartphones","created":"2021-05-17","cited_by_count":1,"area":null},{"id":"2107.10050","title":"You Better Look Twice: a new perspective for designing accurate detectors with reduced computations","created":"2021-07-21","cited_by_count":1,"area":null},{"id":"2110.10842","title":"SMOF: Squeezing More Out of Filters Yields Hardware-Friendly CNN Pruning","created":"2021-10-21","cited_by_count":1,"area":null},{"id":"2209.00961","title":"LiteDepth: Digging into Fast and Accurate Depth Estimation on Mobile Devices","created":"2022-09-02","cited_by_count":1,"area":null},{"id":"2212.09501","title":"NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution","created":"2022-12-15","cited_by_count":1,"area":null},{"id":"2301.00407","title":"MIGPerf: A Comprehensive Benchmark for Deep Learning Training and Inference Workloads on Multi-Instance GPUs","created":"2023-01-01","cited_by_count":1,"area":null},{"id":"2307.13412","title":"Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation","created":"2023-07-25","cited_by_count":1,"area":null},{"id":"2312.08298","title":"Venn: Resource Management for Collaborative Learning Jobs","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2403.00865","title":"Fast and Efficient Local Search for Genetic Programming Based Loss Function Learning","created":"2024-03-01","cited_by_count":1,"area":null},{"id":"2404.13515","title":"FedTrans: Efficient Federated Learning via Multi-Model Transformation","created":"2024-04-21","cited_by_count":1,"area":null},{"id":"2409.01089","title":"CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloads","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2503.00060","title":"SAC-ViT: Semantic-Aware Clustering Vision Transformer with Early Exit","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2106.12810","title":"A Construction Kit for Efficient Low Power Neural Network Accelerator Designs","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2111.13365","title":"Machines & Influence: An Information Systems Lens","created":"2021-11-26","cited_by_count":0,"area":null},{"id":"2302.00514","title":"Towards Implementing Energy-aware Data-driven Intelligence for Smart Health Applications on Mobile Platforms","created":"2023-02-01","cited_by_count":0,"area":null},{"id":"2310.05950","title":"Quantization of Neural Network Equalizers in Optical Fiber Transmission Experiments","created":"2023-09-09","cited_by_count":0,"area":null},{"id":"2403.10984","title":"IoTCO2: Assessing the End-To-End Carbon Footprint of Internet-of-Things-Enabled Deep Learning","created":"2024-03-16","cited_by_count":0,"area":null},{"id":"2405.15644","title":"Harnessing Increased Client Participation with Cohort-Parallel Federated Learning","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2410.06567","title":"Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2504.15649","title":"RepNet-VSR: Reparameterizable Architecture for High-Fidelity Video Super-Resolution","created":"2025-04-22","cited_by_count":0,"area":null},{"id":"2510.10380","title":"FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2511.09828","title":"SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2604.21743","title":"Bridging the Training-Deployment Gap: Gated Encoding and Multi-Scale Refinement for Efficient Quantization-Aware Image Enhancement","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2609.16085","title":"Is INT8 Portable? A Cross-Platform Measurement Study of Quantized Inference on Embedded and Automotive Accelerators","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}