{"total":129,"rows":[{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"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":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133,"area":null},{"id":"2112.02918","title":"When the Curious Abandon Honesty: Federated Learning Is Not Private","created":"2021-12-06","cited_by_count":127,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2106.05022","title":"Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions","created":"2021-06-09","cited_by_count":75,"area":"inference"},{"id":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59,"area":null},{"id":"2107.12422","title":"Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework","created":"2021-07-26","cited_by_count":52,"area":null},{"id":"2102.05775","title":"AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition","created":"2021-02-10","cited_by_count":48,"area":null},{"id":"2207.01076","title":"Divert More Attention to Vision-Language Tracking","created":"2022-07-03","cited_by_count":47,"area":null},{"id":"2103.05861","title":"Manifold Regularized Dynamic Network Pruning","created":"2021-03-10","cited_by_count":43,"area":null},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2106.06468","title":"Locally Sparse Neural Networks for Tabular Biomedical Data","created":"2021-06-11","cited_by_count":34,"area":null},{"id":"2107.11442","title":"Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition","created":"2021-07-23","cited_by_count":33,"area":null},{"id":"2104.11487","title":"Skip-Convolutions for Efficient Video Processing","created":"2021-04-23","cited_by_count":32,"area":null},{"id":"2102.05258","title":"Locally Free Weight Sharing for Network Width Search","created":"2021-02-10","cited_by_count":27,"area":null},{"id":"2105.09121","title":"Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead","created":"2021-05-19","cited_by_count":26,"area":"inference"},{"id":"2110.04456","title":"Deep Joint Source-Channel Coding for Wireless Image Transmission with Adaptive Rate Control","created":"2021-10-09","cited_by_count":26,"area":null},{"id":"2308.15949","title":"Latency-aware Unified Dynamic Networks for Efficient Image Recognition","created":"2023-08-30","cited_by_count":26,"area":null},{"id":"2110.08232","title":"Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction","created":"2021-10-15","cited_by_count":24,"area":null},{"id":"2205.03055","title":"Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism","created":"2022-05-06","cited_by_count":20,"area":null},{"id":"2106.03527","title":"Multi-Exit Semantic Segmentation Networks","created":"2021-06-07","cited_by_count":18,"area":null},{"id":"2205.11269","title":"Dynamic Split Computing for Efficient Deep Edge Intelligence","created":"2022-05-23","cited_by_count":18,"area":null},{"id":"2212.03537","title":"Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning","created":"2022-12-07","cited_by_count":16,"area":null},{"id":"2303.10276","title":"Unleashing the Potential of Spiking Neural Networks by Dynamic Confidence","created":"2023-03-17","cited_by_count":15,"area":null},{"id":"2306.04451","title":"Referring Expression Comprehension Using Language Adaptive Inference","created":"2023-06-06","cited_by_count":15,"area":null},{"id":"2206.07687","title":"Structured Sparsity Learning for Efficient Video Super-Resolution","created":"2022-06-15","cited_by_count":14,"area":null},{"id":"2304.13539","title":"Tensor Decomposition for Model Reduction in Neural Networks: A Review","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2111.09499","title":"Dynamically pruning segformer for efficient semantic segmentation","created":"2021-11-18","cited_by_count":13,"area":null},{"id":"2108.06277","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","created":"2021-08-13","cited_by_count":12,"area":null},{"id":"2205.04908","title":"Shadow-Aware Dynamic Convolution for Shadow Removal","created":"2022-05-10","cited_by_count":11,"area":null},{"id":"2307.10046","title":"Divert More Attention to Vision-Language Object Tracking","created":"2023-07-19","cited_by_count":11,"area":null},{"id":"2505.05279","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","created":"2025-05-08","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":"2501.15316","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","created":"2025-01-25","cited_by_count":10,"area":"moe"},{"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":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2207.13050","title":"Efficient High-Resolution Deep Learning: A Survey","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2307.04963","title":"DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization","created":"2023-07-11","cited_by_count":9,"area":null},{"id":"2506.05709","title":"Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration","created":"2025-06-06","cited_by_count":9,"area":"inference"},{"id":"2307.15049","title":"Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models","created":"2023-07-27","cited_by_count":7,"area":"mllm"},{"id":"2109.10060","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","created":"2021-09-21","cited_by_count":6,"area":null},{"id":"2112.03690","title":"Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization","created":"2021-12-07","cited_by_count":6,"area":null},{"id":"2208.13363","title":"Survey: Exploiting Data Redundancy for Optimization of Deep Learning","created":"2022-08-29","cited_by_count":6,"area":null},{"id":"2209.00839","title":"Human Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks","created":"2022-09-02","cited_by_count":6,"area":null},{"id":"2305.14109","title":"Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2306.08941","title":"Exploring Resolution Fields for Scalable Image Compression with Uncertainty Guidance","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2505.23807","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2202.06084","title":"EREBA: Black-box Energy Testing of Adaptive Neural Networks","created":"2022-02-12","cited_by_count":5,"area":null},{"id":"2205.06404","title":"Fast Conditional Network Compression Using Bayesian HyperNetworks","created":"2022-05-13","cited_by_count":5,"area":null},{"id":"2210.08159","title":"Dynamics-aware Adversarial Attack of Adaptive Neural Networks","created":"2022-10-15","cited_by_count":5,"area":null},{"id":"2303.09736","title":"Dynamic Structure Pruning for Compressing CNNs","created":"2023-03-17","cited_by_count":5,"area":null},{"id":"2412.17121","title":"Scalable Speech Enhancement with Dynamic Channel Pruning","created":"2024-12-22","cited_by_count":5,"area":null},{"id":"2503.16916","title":"Temporal Action Detection Model Compression by Progressive Block Drop","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2106.00645","title":"Hyperspectral Band Selection for Multispectral Image Classification with Convolutional Networks","created":"2021-06-01","cited_by_count":4,"area":null},{"id":"2106.06921","title":"Heterogeneous Federated Learning using Dynamic Model Pruning and Adaptive Gradient","created":"2021-06-13","cited_by_count":4,"area":null},{"id":"2203.13714","title":"Searching for Network Width with Bilaterally Coupled Network","created":"2022-03-25","cited_by_count":4,"area":null},{"id":"2207.06242","title":"SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2302.08571","title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2304.00280","title":"Progressive Channel-Shrinking Network","created":"2023-04-01","cited_by_count":4,"area":null},{"id":"2309.17211","title":"Data-Free Dynamic Compression of CNNs for Tractable Efficiency","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2401.12167","title":"Dynamic Semantic Compression for CNN Inference in Multi-access Edge Computing: A Graph Reinforcement Learning-based Autoencoder","created":"2024-01-19","cited_by_count":4,"area":"deeprl"},{"id":"2507.04879","title":"Adaptive Slimming for Scalable and Efficient Speech Enhancement","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2203.02617","title":"How to Train Unstable Looped Tensor Network","created":"2022-03-05","cited_by_count":3,"area":null},{"id":"2205.00779","title":"Zebra: Memory Bandwidth Reduction for CNN Accelerators With Zero Block Regularization of Activation Maps","created":"2022-05-02","cited_by_count":3,"area":null},{"id":"2210.02570","title":"Revisiting Structured Dropout","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2303.11247","title":"Memorization Capacity of Neural Networks with Conditional Computation","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2304.06305","title":"Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution","created":"2023-04-13","cited_by_count":3,"area":null},{"id":"2310.02544","title":"SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2503.06945","title":"Dynamic Cross-Modal Feature Interaction Network for Hyperspectral and LiDAR Data Classification","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2505.12523","title":"Energy-Aware Deep Learning on Resource-Constrained Hardware","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2505.18451","title":"$\\mu$-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts","created":"2025-05-24","cited_by_count":3,"area":"moe"},{"id":"2602.17145","title":"Bonsai: A Framework for Convolutional Neural Network Acceleration Using Criterion-Based Pruning","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2101.06407","title":"ACP: Automatic Channel Pruning via Clustering and Swarm Intelligence Optimization for CNN","created":"2021-01-16","cited_by_count":2,"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":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2109.04925","title":"Rapid Model Architecture Adaption for Meta-Learning","created":"2021-09-10","cited_by_count":2,"area":null},{"id":"2205.11179","title":"Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking","created":"2022-05-23","cited_by_count":2,"area":null},{"id":"2307.00198","title":"Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler","created":"2023-07-01","cited_by_count":2,"area":null},{"id":"2406.10935","title":"Pick-or-Mix: Dynamic Channel Sampling for ConvNets","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2505.03254","title":"PROM: Prioritize Reduction of Multiplications Over Lower Bit-Widths for Efficient CNNs","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2509.13662","title":"Deep Lookup Network","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2101.11800","title":"AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications","created":"2021-01-28","cited_by_count":1,"area":null},{"id":"2108.12914","title":"Leveraging Transprecision Computing for Machine Vision Applications at the Edge","created":"2021-08-29","cited_by_count":1,"area":null},{"id":"2109.12507","title":"Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better","created":"2021-09-26","cited_by_count":1,"area":"distill"},{"id":"2110.10876","title":"Evolving Transferable Neural Pruning Functions","created":"2021-10-21","cited_by_count":1,"area":null},{"id":"2205.15198","title":"STN: Scalable Tensorizing Networks via Structure-Aware Training and Adaptive Compression","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2207.12065","title":"Dynamic Channel Selection in Self-Supervised Learning","created":"2022-07-25","cited_by_count":1,"area":null},{"id":"2302.10798","title":"Learning a Consensus Sub-Network with Polarization Regularization and One Pass Training","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2309.13077","title":"A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2310.02776","title":"Dynamic Shuffle: An Efficient Channel Mixture Method","created":"2023-10-04","cited_by_count":1,"area":null},{"id":"2407.04871","title":"Improving Knowledge Distillation in Transfer Learning with Layer-wise Learning Rates","created":"2024-07-05","cited_by_count":1,"area":"distill"},{"id":"2411.12781","title":"FGP: Feature-Gradient-Prune for Efficient Convolutional Layer Pruning","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2511.18105","title":"AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2512.20755","title":"Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits","created":"2025-12-23","cited_by_count":1,"area":"inference"},{"id":"2106.06778","title":"Dynamic Clone Transformer for Efficient Convolutional Neural Netwoks","created":"2021-06-12","cited_by_count":0,"area":null},{"id":"2107.11047","title":"Unrealistic Feature Suppression for Generative Adversarial Networks","created":"2021-07-23","cited_by_count":0,"area":null},{"id":"2108.13591","title":"AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks","created":"2021-08-31","cited_by_count":0,"area":null}],"next_cursor":"100"}