{"total":120,"rows":[{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"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":"2110.13981","title":"CHIP: CHannel Independence-based Pruning for Compact Neural Networks","created":"2021-10-26","cited_by_count":78,"area":null},{"id":"2104.03438","title":"Convolutional Neural Network Pruning with Structural Redundancy Reduction","created":"2021-04-08","cited_by_count":73,"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":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56,"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":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2205.13574","title":"Pruning has a disparate impact on model accuracy","created":"2022-05-26","cited_by_count":44,"area":null},{"id":"2205.11098","title":"PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection","created":"2022-05-23","cited_by_count":33,"area":"distill"},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32,"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":"2109.02220","title":"GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization","created":"2021-09-06","cited_by_count":29,"area":null},{"id":"2104.02244","title":"Content-Aware GAN Compression","created":"2021-04-06","cited_by_count":28,"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":"2312.08656","title":"MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training","created":"2023-12-14","cited_by_count":25,"area":null},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24,"area":null},{"id":"2112.15579","title":"Single-Shot Pruning for Offline Reinforcement Learning","created":"2021-12-31","cited_by_count":21,"area":"offlinerl"},{"id":"2204.02738","title":"Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network","created":"2022-04-06","cited_by_count":21,"area":null},{"id":"2208.03324","title":"Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution","created":"2022-08-05","cited_by_count":19,"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":"2209.04766","title":"Towards Sparsification of Graph Neural Networks","created":"2022-09-11","cited_by_count":18,"area":null},{"id":"2406.07929","title":"A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models","created":"2024-06-12","cited_by_count":18,"area":null},{"id":"2211.16667","title":"Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off","created":"2022-11-30","cited_by_count":15,"area":null},{"id":"2108.04811","title":"Binary Complex Neural Network Acceleration on FPGA","created":"2021-08-10","cited_by_count":14,"area":null},{"id":"2206.07311","title":"Can pruning improve certified robustness of neural networks?","created":"2022-06-15","cited_by_count":14,"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":"2110.14895","title":"Pipeline Parallelism for Inference on Heterogeneous Edge Computing","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2106.09144","title":"FORMS: Fine-grained Polarized ReRAM-based In-situ Computation for Mixed-signal DNN Accelerator","created":"2021-06-16","cited_by_count":12,"area":null},{"id":"2207.01578","title":"Quantum Neural Network Compression","created":"2022-07-04","cited_by_count":12,"area":null},{"id":"2207.05049","title":"Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis","created":"2022-07-11","cited_by_count":12,"area":null},{"id":"2210.04311","title":"Pruning Adversarially Robust Neural Networks without Adversarial Examples","created":"2022-10-09","cited_by_count":12,"area":null},{"id":"2409.09953","title":"Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection","created":"2024-09-16","cited_by_count":12,"area":null},{"id":"2401.02938","title":"Fast and Effective Weight Update for Pruned Large Language Models","created":"2024-01-01","cited_by_count":11,"area":null},{"id":"2106.09166","title":"Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI","created":"2021-06-16","cited_by_count":10,"area":null},{"id":"2108.11033","title":"GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity","created":"2021-08-25","cited_by_count":10,"area":"inference"},{"id":"2107.14444","title":"Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2102.02638","title":"Autodidactic Neurosurgeon: Collaborative Deep Inference for Mobile Edge Intelligence via Online Learning","created":"2021-02-02","cited_by_count":8,"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":"2309.03824","title":"Training Acceleration of Low-Rank Decomposed Networks using Sequential Freezing and Rank Quantization","created":"2023-09-07","cited_by_count":8,"area":null},{"id":"2309.12412","title":"Speeding up Resnet Architecture with Layers Targeted Low Rank Decomposition","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2107.02550","title":"Universal approximation and model compression for radial neural networks","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2107.12445","title":"Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compression","created":"2021-07-16","cited_by_count":7,"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":"2210.05211","title":"A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models","created":"2022-10-11","cited_by_count":7,"area":null},{"id":"2507.18725","title":"The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models","created":"2025-07-24","cited_by_count":7,"area":"safety"},{"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":"2202.01341","title":"Robust Binary Models by Pruning Randomly-initialized Networks","created":"2022-02-03","cited_by_count":5,"area":null},{"id":"2302.08878","title":"Less is More: The Influence of Pruning on the Explainability of CNNs","created":"2023-02-17","cited_by_count":5,"area":null},{"id":"2303.13635","title":"Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training","created":"2023-03-22","cited_by_count":5,"area":null},{"id":"2506.06866","title":"SAFE: Finding Sparse and Flat Minima to Improve Pruning","created":"2025-06-07","cited_by_count":5,"area":null},{"id":"2104.05421","title":"NullaNet Tiny: Ultra-low-latency DNN Inference Through Fixed-function Combinational Logic","created":"2021-04-07","cited_by_count":4,"area":null},{"id":"2108.08560","title":"Pruning in the Face of Adversaries","created":"2021-08-19","cited_by_count":4,"area":null},{"id":"2109.05075","title":"On the Compression of Neural Networks Using $\\ell_0$-Norm Regularization and Weight Pruning","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2202.10100","title":"Enabling On-Device Smartphone GPU based Training: Lessons Learned","created":"2022-02-21","cited_by_count":4,"area":null},{"id":"2203.03794","title":"YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers","created":"2022-03-08","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":"2309.06047","title":"Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2411.10507","title":"RedTest: Towards Measuring Redundancy in Deep Neural Networks Effectively","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2505.21571","title":"FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2509.17968","title":"Visual Detector Compression via Location-Aware Discriminant Analysis","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2108.11430","title":"Towards Memory-Efficient Neural Networks via Multi-Level in situ Generation","created":"2021-08-25","cited_by_count":3,"area":null},{"id":"2110.14871","title":"Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks","created":"2021-10-28","cited_by_count":3,"area":null},{"id":"2210.12818","title":"Pushing the Efficiency Limit Using Structured Sparse Convolutions","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2312.12483","title":"SCoTTi: Save Computation at Training Time with an adaptive framework","created":"2023-12-19","cited_by_count":3,"area":null},{"id":"2312.16020","title":"Robust Neural Pruning with Gradient Sampling Optimization for Residual Neural Networks","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2202.05226","title":"Deadwooding: Robust Global Pruning for Deep Neural Networks","created":"2022-02-10","cited_by_count":2,"area":null},{"id":"2207.01260","title":"CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2209.08617","title":"PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems","created":"2022-09-18","cited_by_count":2,"area":null},{"id":"2303.02512","title":"Visual Saliency-Guided Channel Pruning for Deep Visual Detectors in Autonomous Driving","created":"2023-03-04","cited_by_count":2,"area":null},{"id":"2307.06143","title":"Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression","created":"2023-07-12","cited_by_count":2,"area":null},{"id":"2309.06805","title":"FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization","created":"2023-09-13","cited_by_count":2,"area":null},{"id":"2401.16760","title":"One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2403.08261","title":"CoroNetGAN: Controlled Pruning of GANs via Hypernetworks","created":"2024-03-13","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":"2410.08015","title":"Non-transferable Pruning","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2502.16627","title":"Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2506.08267","title":"Sparse Interpretable Deep Learning with LIES Networks for Symbolic Regression","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2512.20814","title":"FedMPDD: Communication-Efficient Federated Learning with Privacy Preservation Attributes via Projected Directional Derivative","created":"2025-12-23","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":"2109.00644","title":"RIFLE: Imputation and Robust Inference from Low Order Marginals","created":"2021-09-01","cited_by_count":1,"area":null},{"id":"2110.10876","title":"Evolving Transferable Neural Pruning Functions","created":"2021-10-21","cited_by_count":1,"area":null},{"id":"2110.15192","title":"RGP: Neural Network Pruning through Its Regular Graph Structure","created":"2021-10-28","cited_by_count":1,"area":null},{"id":"2112.10898","title":"Load-balanced Gather-scatter Patterns for Sparse Deep Neural Networks","created":"2021-12-20","cited_by_count":1,"area":null},{"id":"2204.04416","title":"E^2TAD: An Energy-Efficient Tracking-based Action Detector","created":"2022-04-09","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":"2210.10670","title":"Attaining Class-level Forgetting in Pretrained Model using Few Samples","created":"2022-10-19","cited_by_count":1,"area":null},{"id":"2303.06815","title":"On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2304.01500","title":"Physics-aware Roughness Optimization for Diffractive Optical Neural Networks","created":"2023-04-04","cited_by_count":1,"area":null},{"id":"2312.10181","title":"Integrating Fairness and Model Pruning Through Bi-level Optimization","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2407.20266","title":"Accelerating the Low-Rank Decomposed Models","created":"2024-07-24","cited_by_count":1,"area":null},{"id":"2408.01534","title":"An Adaptive Tensor-Train Decomposition Approach for Efficient Deep Neural Network Compression","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2505.17469","title":"Efficient compression of neural networks and datasets","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2604.06958","title":"ELC: Evidential Lifelong Classifier for Uncertainty Aware Radar Pulse Classification","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2103.10629","title":"Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2105.02954","title":"Deep Neural Networks Based Weight Approximation and Computation Reuse for 2-D Image Classification","created":"2021-04-28","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":"2109.11168","title":"Unified Signal Compression Using a GAN with Iterative Latent Representation Optimization","created":"2021-09-23","cited_by_count":0,"area":null},{"id":"2110.04492","title":"Weight Evolution: Improving Deep Neural Networks Training through Evolving Inferior Weight Values","created":"2021-10-09","cited_by_count":0,"area":null}],"next_cursor":"100"}