{"total":71,"rows":[{"id":"2110.14032","title":"MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge","created":"2021-10-26","cited_by_count":79,"area":null},{"id":"2407.05858","title":"Fast On-device LLM Inference with NPUs","created":"2024-07-08","cited_by_count":62,"area":null},{"id":"2108.13342","title":"DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion","created":"2021-08-30","cited_by_count":57,"area":null},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56,"area":null},{"id":"2209.09476","title":"SparCL: Sparse Continual Learning on the Edge","created":"2022-09-20","cited_by_count":55,"area":null},{"id":"2503.06027","title":"Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models","created":"2025-03-08","cited_by_count":46,"area":null},{"id":"2309.04255","title":"LLMCad: Fast and Scalable On-device Large Language Model Inference","created":"2023-09-08","cited_by_count":45,"area":null},{"id":"2103.03467","title":"Teachers Do More Than Teach: Compressing Image-to-Image Models","created":"2021-03-05","cited_by_count":37,"area":null},{"id":"2108.08910","title":"Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search","created":"2021-08-18","cited_by_count":34,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2202.04736","title":"Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets","created":"2022-02-09","cited_by_count":27,"area":null},{"id":"2106.09857","title":"Effective Model Sparsification by Scheduled Grow-and-Prune Methods","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2311.10986","title":"EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge","created":"2023-11-18","cited_by_count":21,"area":null},{"id":"2207.12577","title":"Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution","created":"2022-07-25","cited_by_count":20,"area":null},{"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,"area":null},{"id":"2309.07438","title":"Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges","created":"2023-09-14","cited_by_count":14,"area":null},{"id":"2103.15750","title":"Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design","created":"2021-03-25","cited_by_count":13,"area":null},{"id":"2305.12718","title":"HighLight: Efficient and Flexible DNN Acceleration with Hierarchical Structured Sparsity","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2401.16720","title":"SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing","created":"2024-01-30","cited_by_count":12,"area":null},{"id":"2209.11204","title":"Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training","created":"2022-09-22","cited_by_count":11,"area":null},{"id":"2312.15322","title":"Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2102.06336","title":"Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2304.10618","title":"ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks","created":"2023-04-20","cited_by_count":8,"area":null},{"id":"2309.15467","title":"Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey","created":"2023-09-27","cited_by_count":8,"area":null},{"id":"2111.11581","title":"Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration","created":"2021-11-22","cited_by_count":7,"area":null},{"id":"2204.02965","title":"LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2206.02424","title":"Slim-neck by GSConv: A lightweight-design for real-time detector architectures","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2308.05170","title":"FPGA Resource-aware Structured Pruning for Real-Time Neural Networks","created":"2023-08-09","cited_by_count":7,"area":null},{"id":"2112.02644","title":"Boosting Mobile CNN Inference through Semantic Memory","created":"2021-12-05","cited_by_count":6,"area":null},{"id":"2206.07446","title":"Boosting DNN Cold Inference on Edge Devices","created":"2022-06-15","cited_by_count":6,"area":null},{"id":"2212.05122","title":"All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management","created":"2022-12-09","cited_by_count":5,"area":null},{"id":"2301.10388","title":"SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators","created":"2023-01-25","cited_by_count":5,"area":null},{"id":"2309.13015","title":"Efficient N:M Sparse DNN Training Using Algorithm, Architecture, and Dataflow Co-Design","created":"2023-09-22","cited_by_count":5,"area":null},{"id":"2109.03513","title":"Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks","created":"2021-09-08","cited_by_count":4,"area":null},{"id":"2210.08578","title":"Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices","created":"2022-10-16","cited_by_count":4,"area":null},{"id":"2301.04954","title":"Reaching the Edge of the Edge: Image Analysis in Space","created":"2023-01-12","cited_by_count":4,"area":null},{"id":"2303.02191","title":"R-TOSS: A Framework for Real-Time Object Detection using Semi-Structured Pruning","created":"2023-03-03","cited_by_count":4,"area":null},{"id":"2401.09068","title":"DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning","created":"2024-01-17","cited_by_count":4,"area":null},{"id":"2402.17862","title":"REPrune: Channel Pruning via Kernel Representative Selection","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2403.00176","title":"SoD$^2$: Statically Optimizing Dynamic Deep Neural Network","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2301.10835","title":"When Layers Play the Lottery, all Tickets Win at Initialization","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2504.07635","title":"Generative Artificial Intelligence for Internet of Things Computing: A Systematic Survey","created":"2025-04-10","cited_by_count":3,"area":null},{"id":"2106.14943","title":"Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search","created":"2021-06-28","cited_by_count":2,"area":null},{"id":"2206.15014","title":"Compressing Pre-trained Transformers via Low-Bit NxM Sparsity for Natural Language Understanding","created":"2022-06-30","cited_by_count":2,"area":null},{"id":"2207.09258","title":"EVE: Environmental Adaptive Neural Network Models for Low-power Energy Harvesting System","created":"2022-07-14","cited_by_count":2,"area":null},{"id":"2310.09667","title":"Edge-InversionNet: Enabling Efficient Inference of InversionNet on Edge Devices","created":"2023-10-14","cited_by_count":2,"area":null},{"id":"2408.03913","title":"AdapMTL: Adaptive Pruning Framework for Multitask Learning Model","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2502.07820","title":"Low-Rank Compression for IMC Arrays","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2511.16298","title":"Optimizing 3D Gaussian Splattering for Mobile GPUs","created":"2025-11-20","cited_by_count":2,"area":null},{"id":"2101.00745","title":"DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel Convolutions","created":"2021-01-04","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":"2207.00068","title":"Sparse Periodic Systolic Dataflow for Lowering Latency and Power Dissipation of Convolutional Neural Network Accelerators","created":"2022-06-30","cited_by_count":1,"area":null},{"id":"2301.09813","title":"Slice-and-Forge: Making Better Use of Caches for Graph Convolutional Network Accelerators","created":"2023-01-24","cited_by_count":1,"area":null},{"id":"2305.18954","title":"Towards Machine Learning and Inference for Resource-constrained MCUs","created":"2023-05-30","cited_by_count":1,"area":null},{"id":"2408.05363","title":"AyE-Edge: Automated Deployment Space Search Empowering Accuracy yet Efficient Real-Time Object Detection on the Edge","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2510.13405","title":"Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Apps","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2602.15379","title":"FlashMem: Supporting Modern DNN Workloads on Mobile with GPU Memory Hierarchy Optimizations","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2104.00258","title":"Pinpointing the Memory Behaviors of DNN Training","created":"2021-04-01","cited_by_count":0,"area":null},{"id":"2106.08301","title":"Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2201.04402","title":"MoViDNN: A Mobile Platform for Evaluating Video Quality Enhancement with Deep Neural Networks","created":"2022-01-12","cited_by_count":0,"area":null},{"id":"2206.03326","title":"Compilation and Optimizations for Efficient Machine Learning on Embedded Systems","created":"2022-06-06","cited_by_count":0,"area":null},{"id":"2206.10620","title":"CoCoPIE XGen: A Full-Stack AI-Oriented Optimizing Framework","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2303.11291","title":"Mobiprox: Supporting Dynamic Approximate Computing on Mobiles","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2304.04120","title":"Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruning","created":"2023-04-08","cited_by_count":0,"area":null},{"id":"2305.13232","title":"Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2402.04325","title":"Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2407.19644","title":"Realizing Unaligned Block-wise Pruning for DNN Acceleration on Mobile Devices","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2501.04213","title":"UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles","created":"2025-01-08","cited_by_count":0,"area":null},{"id":"2503.17959","title":"Dynamic Gradient Sparse Update for Edge Training","created":"2025-03-23","cited_by_count":0,"area":null},{"id":"2603.21508","title":"Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2610.00465","title":"AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}