{"total":70,"rows":[{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"area":null},{"id":"2310.18356","title":"LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery","created":"2023-10-24","cited_by_count":38,"area":null},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32,"area":null},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31,"area":null},{"id":"2211.00454","title":"PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physics","created":"2022-11-01","cited_by_count":26,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22,"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":"2406.07831","title":"ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models","created":"2024-06-12","cited_by_count":19,"area":null},{"id":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","cited_by_count":19,"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":"2308.10438","title":"Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks","created":"2023-08-21","cited_by_count":15,"area":null},{"id":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2207.04089","title":"SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance","created":"2022-07-08","cited_by_count":9,"area":null},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","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":"2503.07940","title":"BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes","created":"2025-03-11","cited_by_count":8,"area":null},{"id":"2207.14200","title":"CrAM: A Compression-Aware Minimizer","created":"2022-07-28","cited_by_count":7,"area":null},{"id":"2402.15978","title":"Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood","created":"2024-02-25","cited_by_count":7,"area":null},{"id":"2209.04551","title":"Sparsity-guided Network Design for Frame Interpolation","created":"2022-09-09","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":"2509.14230","title":"NIRVANA: Structured Pruning Reimagined for Large Language Model Compression","created":"2025-09-17","cited_by_count":6,"area":null},{"id":"2303.04555","title":"Streaming Kernel PCA Algorithm With Small Space","created":"2023-03-08","cited_by_count":5,"area":null},{"id":"2501.09464","title":"Pruning for Sparse Diffusion Models based on Gradient Flow","created":"2025-01-16","cited_by_count":5,"area":"diffusion"},{"id":"2206.14056","title":"Deep Neural Networks pruning via the Structured Perspective Regularization","created":"2022-06-28","cited_by_count":4,"area":null},{"id":"2404.10824","title":"Decoupled Weight Decay for Any $p$ Norm","created":"2024-04-16","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":"2204.06404","title":"Receding Neuron Importances for Structured Pruning","created":"2022-04-13","cited_by_count":3,"area":null},{"id":"2301.00335","title":"Pruning Before Training May Improve Generalization, Provably","created":"2023-01-01","cited_by_count":3,"area":null},{"id":"2307.11128","title":"Approximate Computing Survey, Part II: Application-Specific & Architectural Approximation Techniques and Applications","created":"2023-07-20","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":"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":"2408.14601","title":"3D Point Cloud Network Pruning: When Some Weights Do not Matter","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2505.19427","title":"WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference","created":"2025-05-26","cited_by_count":3,"area":"moe"},{"id":"2506.23675","title":"Pruning by Block Benefit: Exploring the Properties of Vision Transformer Blocks during Domain Adaptation","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2209.05683","title":"One-shot Network Pruning at Initialization with Discriminative Image Patches","created":"2022-09-13","cited_by_count":2,"area":null},{"id":"2301.00327","title":"Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK","created":"2023-01-01","cited_by_count":2,"area":null},{"id":"2305.17559","title":"Pruning at Initialization -- A Sketching Perspective","created":"2023-05-27","cited_by_count":2,"area":null},{"id":"2307.11904","title":"Model Compression Methods for YOLOv5: A Review","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2507.12771","title":"Local Representative Token Guided Merging for Text-to-Image Generation","created":"2025-07-17","cited_by_count":2,"area":"diffusion"},{"id":"2607.06922","title":"Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2209.09389","title":"State-driven Implicit Modeling for Sparsity and Robustness in Neural Networks","created":"2022-09-19","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":"2404.08111","title":"S3Editor: A Sparse Semantic-Disentangled Self-Training Framework for Face Video Editing","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2405.17746","title":"Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective","created":"2024-05-28","cited_by_count":1,"area":"safety"},{"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":"2501.13439","title":"One-Cycle Structured Pruning via Stability-Driven Subnetwork Search","created":"2025-01-23","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":"2511.19566","title":"ModHiFi: Identifying High Fidelity predictive components for Model Modification","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2601.02759","title":"Toward Zero-Shot Point Cloud Registration Across Diverse Scales, Scenes, and Sensor Setups","created":"2026-01-06","cited_by_count":1,"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":"2210.00181","title":"EAPruning: Evolutionary Pruning for Vision Transformers and CNNs","created":"2022-10-01","cited_by_count":0,"area":null},{"id":"2305.18030","title":"Automated Search-Space Generation Neural Architecture Search","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2312.03889","title":"A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2312.06872","title":"ELSA: Partial Weight Freezing for Overhead-Free Sparse Network Deployment","created":"2023-12-11","cited_by_count":0,"area":null},{"id":"2403.05123","title":"ECToNAS: Evolutionary Cross-Topology Neural Architecture Search","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2403.14120","title":"Advancing IIoT with Over-the-Air Federated Learning: The Role of Iterative Magnitude Pruning","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2409.02052","title":"Robust Fourier Neural Networks","created":"2024-09-03","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},{"id":"2502.17071","title":"Systematic Weight Evaluation for Pruning Large Language Models: Enhancing Performance and Sustainability","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2506.20152","title":"Loss-Aware Automatic Selection of Structured Pruning Criteria for Deep Neural Network Acceleration","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2509.16833","title":"SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2510.08728","title":"Structured Output Regularization: a framework for few-shot transfer learning","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.10764","title":"Optimally Deep Networks -- Adapting Model Depth to Datasets for Superior Efficiency","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2510.14463","title":"Pruning Overparameterized Multi-Task Networks for Degraded Web Image Restoration","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.18636","title":"C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2601.20301","title":"Towards Compact and Robust DNNs via Compression-aware Sharpness Minimization","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.22537","title":"LUMOS: Democratizing SciML Workflows with L0-Regularized Learning for Unified Feature and Parameter Adaptation","created":"2026-02-26","cited_by_count":0,"area":null}],"next_cursor":null}