{"total":118,"rows":[{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203,"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":"2305.10924","title":"Structural Pruning for Diffusion Models","created":"2023-05-18","cited_by_count":195,"area":"diffusion"},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131,"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":"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":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2210.06659","title":"Structural Pruning via Latency-Saliency Knapsack","created":"2022-10-13","cited_by_count":41,"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":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32,"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":"2102.05258","title":"Locally Free Weight Sharing for Network Width Search","created":"2021-02-10","cited_by_count":27,"area":null},{"id":"2103.01542","title":"TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning","created":"2021-03-02","cited_by_count":25,"area":null},{"id":"2105.03193","title":"Network Pruning That Matters: A Case Study on Retraining Variants","created":"2021-05-07","cited_by_count":25,"area":null},{"id":"2207.10909","title":"DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection","created":"2022-07-22","cited_by_count":25,"area":null},{"id":"2301.03831","title":"Dynamic Grained Encoder for Vision Transformers","created":"2023-01-10","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":"2206.10451","title":"Winning the Lottery Ahead of Time: Efficient Early Network Pruning","created":"2022-06-21","cited_by_count":21,"area":null},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","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":"2305.19454","title":"Dynamic Sparsity Is Channel-Level Sparsity Learner","created":"2023-05-30","cited_by_count":18,"area":null},{"id":"2305.00097","title":"NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation","created":"2023-04-28","cited_by_count":16,"area":"safety"},{"id":"2204.12266","title":"Attentive Fine-Grained Structured Sparsity for Image Restoration","created":"2022-04-26","cited_by_count":12,"area":null},{"id":"2211.02206","title":"Soft Masking for Cost-Constrained Channel Pruning","created":"2022-11-04","cited_by_count":12,"area":null},{"id":"2407.04208","title":"AMD: Automatic Multi-step Distillation of Large-scale Vision Models","created":"2024-07-05","cited_by_count":12,"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":"2303.07868","title":"DynaMask: Dynamic Mask Selection for Instance Segmentation","created":"2023-03-14","cited_by_count":10,"area":null},{"id":"2312.05875","title":"Class-Aware Pruning for Efficient Neural Networks","created":"2023-12-10","cited_by_count":9,"area":null},{"id":"2110.10811","title":"HALP: Hardware-Aware Latency Pruning","created":"2021-10-20","cited_by_count":8,"area":null},{"id":"2403.18955","title":"Structurally Prune Anything: Any Architecture, Any Framework, Any Time","created":"2024-03-03","cited_by_count":8,"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":"2405.02717","title":"AFter: Attention-based Fusion Router for RGBT Tracking","created":"2024-05-04","cited_by_count":7,"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":"2211.12714","title":"Developmental Plasticity-inspired Adaptive Pruning for Deep Spiking and Artificial Neural Networks","created":"2022-11-23","cited_by_count":6,"area":null},{"id":"2312.09411","title":"OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2403.07688","title":"Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2203.02651","title":"Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning","created":"2022-03-05","cited_by_count":5,"area":null},{"id":"2209.13590","title":"Sauron U-Net: Simple automated redundancy elimination in medical image segmentation via filter pruning","created":"2022-09-27","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":"2306.04147","title":"CFDP: Common Frequency Domain Pruning","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2504.02168","title":"MDP: Multidimensional Vision Model Pruning with Latency Constraint","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2603.01685","title":"FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2106.14126","title":"AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning","created":"2021-06-27","cited_by_count":4,"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":"2201.11103","title":"Auto-Compressing Subset Pruning for Semantic Image Segmentation","created":"2022-01-26","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":"2204.11444","title":"Boosting Pruned Networks with Linear Over-parameterization","created":"2022-04-25","cited_by_count":4,"area":null},{"id":"2207.02632","title":"Network Pruning via Feature Shift Minimization","created":"2022-07-06","cited_by_count":4,"area":null},{"id":"2211.10285","title":"A Fair Loss Function for Network Pruning","created":"2022-11-18","cited_by_count":4,"area":null},{"id":"2308.06755","title":"Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining","created":"2023-08-13","cited_by_count":4,"area":null},{"id":"2308.13783","title":"Generalized Lightness Adaptation with Channel Selective Normalization","created":"2023-08-26","cited_by_count":4,"area":null},{"id":"2406.12079","title":"Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2409.09085","title":"HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruning","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2201.10520","title":"Adaptive Activation-based Structured Pruning","created":"2022-01-21","cited_by_count":3,"area":null},{"id":"2308.03409","title":"DiT: Efficient Vision Transformers with Dynamic Token Routing","created":"2023-08-07","cited_by_count":3,"area":null},{"id":"2404.08016","title":"ONNXPruner: ONNX-Based General Model Pruning Adapter","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2502.17941","title":"Optimal Brain Apoptosis","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2507.03117","title":"BLaST: High Performance Inference and Pretraining using BLock Sparse Transformers","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2508.05521","title":"Optimal Brain Connection: Towards Efficient Structural Pruning","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2604.24380","title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","created":"2026-04-27","cited_by_count":3,"area":"mllm"},{"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":"2403.06417","title":"Enhanced Sparsification via Stimulative Training","created":"2024-03-11","cited_by_count":2,"area":"distill"},{"id":"2405.01041","title":"Efficient and Flexible Method for Reducing Moderate-size Deep Neural Networks with Condensation","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2410.08015","title":"Non-transferable Pruning","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2501.01118","title":"Pruning-based Data Selection and Network Fusion for Efficient Deep Learning","created":"2025-01-02","cited_by_count":2,"area":null},{"id":"2506.12041","title":"Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning","created":"2025-05-24","cited_by_count":2,"area":null},{"id":"2104.08446","title":"Towards Efficient Convolutional Network Models with Filter Distribution Templates","created":"2021-04-17","cited_by_count":1,"area":null},{"id":"2202.12417","title":"Optimal channel selection with discrete QCQP","created":"2022-02-24","cited_by_count":1,"area":null},{"id":"2207.04227","title":"On the Robustness and Anomaly Detection of Sparse Neural Networks","created":"2022-07-09","cited_by_count":1,"area":null},{"id":"2212.12921","title":"Learning k-Level Structured Sparse Neural Networks Using Group Envelope Regularization","created":"2022-12-25","cited_by_count":1,"area":null},{"id":"2301.12187","title":"Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming","created":"2023-01-28","cited_by_count":1,"area":null},{"id":"2304.13397","title":"Filter Pruning via Filters Similarity in Consecutive Layers","created":"2023-04-26","cited_by_count":1,"area":null},{"id":"2305.14403","title":"Layer-adaptive Structured Pruning Guided by Latency","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2403.00155","title":"Towards Explaining Deep Neural Network Compression Through a Probabilistic Latent Space","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2405.10271","title":"Pruning Federated Models through Loss Landscape Analysis and Client Agreement Scoring","created":"2024-05-16","cited_by_count":1,"area":null},{"id":"2406.03879","title":"Decay Pruning Method: Smooth Pruning With a Self-Rectifying Procedure","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2501.15240","title":"Hardware-Aware DNN Compression for Homogeneous Edge Devices","created":"2025-01-25","cited_by_count":1,"area":null},{"id":"2501.15592","title":"Information Consistent Pruning: How to Efficiently Search for Sparse Networks?","created":"2025-01-26","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":"2502.12455","title":"DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs","created":"2025-02-18","cited_by_count":1,"area":"moe"},{"id":"2504.05621","title":"Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanism","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2507.20749","title":"Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study","created":"2025-07-28","cited_by_count":1,"area":"mllm"},{"id":"2104.13993","title":"Filter Distribution Templates in Convolutional Networks for Image Classification Tasks","created":"2021-04-28","cited_by_count":0,"area":null},{"id":"2105.10436","title":"Compressing Deep CNNs using Basis Representation and Spectral Fine-tuning","created":"2021-05-21","cited_by_count":0,"area":null},{"id":"2107.00070","title":"Dep-$L_0$: Improving $L_0$-based Network Sparsification via Dependency Modeling","created":"2021-06-30","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},{"id":"2110.10864","title":"Class-Discriminative CNN Compression","created":"2021-10-21","cited_by_count":0,"area":null},{"id":"2209.03534","title":"CWP: Instance complexity weighted channel-wise soft masks for network pruning","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2209.13071","title":"Diversified Dynamic Routing for Vision Tasks","created":"2022-09-26","cited_by_count":0,"area":"moe"},{"id":"2211.05488","title":"ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2308.04470","title":"D-Score: A Synapse-Inspired Approach for Filter Pruning","created":"2023-08-08","cited_by_count":0,"area":null},{"id":"2403.15432","title":"BRIEDGE: EEG-Adaptive Edge AI for Multi-Brain to Multi-Robot Interaction","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2404.00466","title":"Computation and Communication Efficient Lightweighting Vertical Federated Learning for Smart Building IoT","created":"2024-03-30","cited_by_count":0,"area":null},{"id":"2405.17506","title":"Subspace Node Pruning","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2405.19652","title":"Dual sparse training framework: inducing activation map sparsity via Transformed $\\ell1$ regularization","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2406.12315","title":"A Comprehensive Study of Structural Pruning for Vision Models","created":"2024-06-18","cited_by_count":0,"area":null},{"id":"2408.16233","title":"PSE-Net: Channel Pruning for Convolutional Neural Networks with Parallel-subnets Estimator","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2409.03777","title":"A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs","created":"2024-08-22","cited_by_count":0,"area":null}],"next_cursor":"100"}