{"total":90,"rows":[{"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":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79,"area":null},{"id":"2203.08243","title":"Unified Visual Transformer Compression","created":"2022-03-15","cited_by_count":79,"area":null},{"id":"2110.13981","title":"CHIP: CHannel Independence-based Pruning for Compact Neural Networks","created":"2021-10-26","cited_by_count":78,"area":null},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70,"area":null},{"id":"2303.04935","title":"X-Pruner: eXplainable Pruning for Vision Transformers","created":"2023-03-08","cited_by_count":68,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2106.03225","title":"Efficient Lottery Ticket Finding: Less Data is More","created":"2021-06-06","cited_by_count":44,"area":null},{"id":"2211.12905","title":"GhostNetV2: Enhance Cheap Operation with Long-Range Attention","created":"2022-11-23","cited_by_count":44,"area":null},{"id":"2103.05861","title":"Manifold Regularized Dynamic Network Pruning","created":"2021-03-10","cited_by_count":43,"area":null},{"id":"2103.00841","title":"Learning Frequency Domain Approximation for Binary Neural Networks","created":"2021-03-01","cited_by_count":38,"area":null},{"id":"2305.02299","title":"Dynamic Sparse Training with Structured Sparsity","created":"2023-05-03","cited_by_count":38,"area":null},{"id":"2203.15794","title":"CHEX: CHannel EXploration for CNN Model Compression","created":"2022-03-29","cited_by_count":36,"area":null},{"id":"2106.02898","title":"Dynamic Resolution Network","created":"2021-06-05","cited_by_count":31,"area":null},{"id":"2102.03214","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","created":"2021-02-05","cited_by_count":30,"area":null},{"id":"2110.11395","title":"SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning","created":"2021-10-19","cited_by_count":30,"area":null},{"id":"2109.02220","title":"GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization","created":"2021-09-06","cited_by_count":29,"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":"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":"2105.10533","title":"BCNet: Searching for Network Width with Bilaterally Coupled Network","created":"2021-05-21","cited_by_count":23,"area":null},{"id":"2301.09422","title":"HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks","created":"2023-01-20","cited_by_count":20,"area":null},{"id":"2403.14729","title":"Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch","created":"2024-03-21","cited_by_count":20,"area":null},{"id":"2105.14797","title":"RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks","created":"2021-05-31","cited_by_count":19,"area":null},{"id":"2110.01397","title":"RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging","created":"2021-09-30","cited_by_count":19,"area":null},{"id":"2305.19454","title":"Dynamic Sparsity Is Channel-Level Sparsity Learner","created":"2023-05-30","cited_by_count":18,"area":null},{"id":"2403.12983","title":"OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization","created":"2024-03-02","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":"2403.17921","title":"The Need for Speed: Pruning Transformers with One Recipe","created":"2024-03-26","cited_by_count":16,"area":null},{"id":"2407.02068","title":"LPViT: Low-Power Semi-structured Pruning for Vision Transformers","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2305.17235","title":"COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models","created":"2023-05-26","cited_by_count":14,"area":null},{"id":"2207.09455","title":"To update or not to update? Neurons at equilibrium in deep models","created":"2022-07-19","cited_by_count":13,"area":null},{"id":"2303.08595","title":"Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions","created":"2023-03-14","cited_by_count":11,"area":null},{"id":"2401.10341","title":"ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2203.01587","title":"Multi-Tailed Vision Transformer for Efficient Inference","created":"2022-03-03","cited_by_count":10,"area":null},{"id":"2303.11923","title":"Performance-aware Approximation of Global Channel Pruning for Multitask CNNs","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2401.06426","title":"UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer","created":"2024-01-12","cited_by_count":9,"area":null},{"id":"2403.19490","title":"Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment","created":"2024-03-28","cited_by_count":9,"area":null},{"id":"2101.08525","title":"GhostSR: Learning Ghost Features for Efficient Image Super-Resolution","created":"2021-01-21","cited_by_count":8,"area":null},{"id":"2103.01847","title":"Network Pruning via Resource Reallocation","created":"2021-03-02","cited_by_count":6,"area":null},{"id":"2103.10858","title":"Toward Compact Deep Neural Networks via Energy-Aware Pruning","created":"2021-03-19","cited_by_count":6,"area":null},{"id":"2105.03679","title":"EZCrop: Energy-Zoned Channels for Robust Output Pruning","created":"2021-05-08","cited_by_count":6,"area":null},{"id":"2110.10921","title":"CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization","created":"2021-10-21","cited_by_count":6,"area":null},{"id":"2406.11257","title":"ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking","created":"2024-06-17","cited_by_count":6,"area":null},{"id":"2201.06776","title":"Pruning-aware Sparse Regularization for Network Pruning","created":"2022-01-18","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":"2406.04549","title":"Concurrent Training and Layer Pruning of Deep Neural Networks","created":"2024-06-06","cited_by_count":5,"area":null},{"id":"2111.09635","title":"Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy","created":"2021-11-18","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":"2402.17862","title":"REPrune: Channel Pruning via Kernel Representative Selection","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2503.09657","title":"T\\'yr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2109.09310","title":"Learning Versatile Convolution Filters for Efficient Visual Recognition","created":"2021-09-20","cited_by_count":3,"area":null},{"id":"2201.10520","title":"Adaptive Activation-based Structured Pruning","created":"2022-01-21","cited_by_count":3,"area":null},{"id":"2205.04650","title":"Robust Learning of Parsimonious Deep Neural Networks","created":"2022-05-10","cited_by_count":3,"area":null},{"id":"2212.14158","title":"BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2405.03089","title":"Structure-Preserving Network Compression Via Low-Rank Induced Training Through Linear Layers Composition","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2303.03645","title":"Filter Pruning based on Information Capacity and Independence","created":"2023-03-07","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":"2310.06344","title":"Filter Pruning For CNN With Enhanced Linear Representation Redundancy","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2311.17493","title":"Towards Higher Ranks via Adversarial Weight Pruning","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2501.03289","title":"Adaptive Pruning of Pretrained Transformer via Differential Inclusions","created":"2025-01-06","cited_by_count":2,"area":null},{"id":"2110.12477","title":"Exploring Gradient Flow Based Saliency for DNN Model Compression","created":"2021-10-24","cited_by_count":1,"area":null},{"id":"2204.00783","title":"Supervised Robustness-preserving Data-free Neural Network Pruning","created":"2022-04-02","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":"2310.06218","title":"SUBP: Soft Uniform Block Pruning for 1xN Sparse CNNs Multithreading Acceleration","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2411.09127","title":"Complexity-Aware Training of Deep Neural Networks for Optimal Structure Discovery","created":"2024-11-14","cited_by_count":1,"area":null},{"id":"2502.03658","title":"Advancing Weight and Channel Sparsification with Enhanced Saliency","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2502.09125","title":"Enhanced Structured Lasso Pruning with Class-wise Information","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2506.01229","title":"Structured Pruning and Quantization for Learned Image Compression","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2110.12844","title":"Reconstructing Pruned Filters using Cheap Spatial Transformations","created":"2021-10-25","cited_by_count":0,"area":null},{"id":"2210.11114","title":"Pruning by Active Attention Manipulation","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2308.10839","title":"Vision Transformer Pruning Via Matrix Decomposition","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2308.13818","title":"Packet Header Recognition Utilizing an All-Optical Reservoir Based on Reinforcement-Learning-Optimized Double-Ring Resonator","created":"2023-08-26","cited_by_count":0,"area":null},{"id":"2312.11555","title":"CR-SFP: Learning Consistent Representation for Soft Filter Pruning","created":"2023-12-17","cited_by_count":0,"area":null},{"id":"2405.10802","title":"Reduced storage direct tensor ring decomposition for convolutional neural networks compression","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2406.17117","title":"Speeding Up Image Classifiers with Little Companions","created":"2024-06-24","cited_by_count":0,"area":null},{"id":"2408.16289","title":"Convolutional Neural Network Compression Based on Low-Rank Decomposition","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2409.03555","title":"Unified Framework for Pre-trained Neural Network Compression via Decomposition and Optimized Rank Selection","created":"2024-09-05","cited_by_count":0,"area":null},{"id":"2410.07046","title":"S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2501.11135","title":"Playing the Lottery With Concave Regularizers for Sparse Trainable Neural Networks","created":"2025-01-19","cited_by_count":0,"area":null},{"id":"2505.13225","title":"CoSeP: Complementary Separability Pruning via Class-Separability Clustering","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2507.14171","title":"IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2507.22527","title":"FGFP: A Fractional Gaussian Filter and Pruning for Deep Neural Networks Compression","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2511.06265","title":"CAMP-HiVe: Cyclic Pair Merging based Efficient DNN Pruning with Hessian-Vector Approximation for Resource-Constrained Systems","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2512.13175","title":"Seeing the Whole Picture: Distribution-Guided Data-Free Distillation for Semantic Segmentation","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2603.12222","title":"HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2603.13186","title":"Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights","created":"2026-03-13","cited_by_count":0,"area":null}],"next_cursor":null}