{"total":82,"rows":[{"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":"2207.09353","title":"Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications","created":"2022-07-19","cited_by_count":175,"area":null},{"id":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133,"area":null},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131,"area":null},{"id":"2104.02151","title":"Distributed Learning in Wireless Networks: Recent Progress and Future Challenges","created":"2021-04-05","cited_by_count":129,"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":"2103.10559","title":"CDFI: Compression-Driven Network Design for Frame Interpolation","created":"2021-03-18","cited_by_count":56,"area":null},{"id":"2205.05996","title":"Blueprint Separable Residual Network for Efficient Image Super-Resolution","created":"2022-05-12","cited_by_count":44,"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":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","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":"2103.01542","title":"TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning","created":"2021-03-02","cited_by_count":25,"area":null},{"id":"2109.12338","title":"Distribution-sensitive Information Retention for Accurate Binary Neural Network","created":"2021-09-25","cited_by_count":25,"area":null},{"id":"2308.07209","title":"Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning","created":"2023-08-14","cited_by_count":23,"area":null},{"id":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22,"area":null},{"id":"2209.08554","title":"Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions","created":"2022-09-18","cited_by_count":20,"area":null},{"id":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2107.08591","title":"Double Similarity Distillation for Semantic Image Segmentation","created":"2021-07-19","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":"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":"2208.04952","title":"Continual Prune-and-Select: Class-incremental learning with specialized subnetworks","created":"2022-08-09","cited_by_count":17,"area":null},{"id":"2105.13011","title":"Neural Network Training Using $\\ell_1$-Regularization and Bi-fidelity Data","created":"2021-05-27","cited_by_count":16,"area":null},{"id":"2207.12534","title":"Trainability Preserving Neural Pruning","created":"2022-07-25","cited_by_count":16,"area":null},{"id":"2403.15173","title":"LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels","created":"2024-03-22","cited_by_count":15,"area":null},{"id":"2107.02306","title":"Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity","created":"2021-07-05","cited_by_count":14,"area":null},{"id":"2203.02026","title":"Provable and Efficient Continual Representation Learning","created":"2022-03-03","cited_by_count":14,"area":null},{"id":"2102.03773","title":"SeReNe: Sensitivity based Regularization of Neurons for Structured Sparsity in Neural Networks","created":"2021-02-07","cited_by_count":12,"area":null},{"id":"2107.10624","title":"LANA: Latency Aware Network Acceleration","created":"2021-07-12","cited_by_count":11,"area":"distill"},{"id":"2109.10795","title":"Neural network relief: a pruning algorithm based on neural activity","created":"2021-09-22","cited_by_count":10,"area":null},{"id":"2205.06701","title":"Knowledge Distillation Meets Open-Set Semi-Supervised Learning","created":"2022-05-13","cited_by_count":9,"area":"distill"},{"id":"2206.02976","title":"Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2209.14881","title":"Sequential Attention for Feature Selection","created":"2022-09-29","cited_by_count":9,"area":null},{"id":"2301.07966","title":"Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions","created":"2023-01-19","cited_by_count":8,"area":null},{"id":"2102.00160","title":"Deep Model Compression based on the Training History","created":"2021-01-30","cited_by_count":7,"area":null},{"id":"2104.09252","title":"Learning on Hardware: A Tutorial on Neural Network Accelerators and Co-Processors","created":"2021-04-19","cited_by_count":6,"area":null},{"id":"2209.04551","title":"Sparsity-guided Network Design for Frame Interpolation","created":"2022-09-09","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":"2404.13648","title":"Data-independent Module-aware Pruning for Hierarchical Vision Transformers","created":"2024-04-21","cited_by_count":6,"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":"2410.19274","title":"Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2108.09081","title":"FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update","created":"2021-08-20","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":"2206.08869","title":"Fast Lossless Neural Compression with Integer-Only Discrete Flows","created":"2022-06-17","cited_by_count":4,"area":null},{"id":"2306.02433","title":"Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2104.08314","title":"High Performance Convolution Using Sparsity and Patterns for Inference in Deep Convolutional Neural Networks","created":"2021-04-16","cited_by_count":3,"area":null},{"id":"2105.01064","title":"Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2109.15014","title":"Deep Neural Compression Via Concurrent Pruning and Self-Distillation","created":"2021-09-30","cited_by_count":3,"area":"distill"},{"id":"2206.01509","title":"Canonical convolutional neural networks","created":"2022-06-03","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":"2402.19264","title":"T3DNet: Compressing Point Cloud Models for Lightweight 3D Recognition","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2406.19995","title":"Single Parent Family: A Spectrum of Family Members from a Single Pre-Trained Foundation Model","created":"2024-06-28","cited_by_count":3,"area":null},{"id":"2502.00899","title":"HASSLE-free: A unified Framework for Sparse plus Low-Rank Matrix Decomposition for LLMs","created":"2025-02-02","cited_by_count":3,"area":null},{"id":"2111.05950","title":"Self-Compression in Bayesian Neural Networks","created":"2021-11-10","cited_by_count":2,"area":null},{"id":"2212.00291","title":"The Effect of Data Dimensionality on Neural Network Prunability","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2303.08970","title":"Gated Compression Layers for Efficient Always-On Models","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2303.09650","title":"Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution","created":"2023-03-16","cited_by_count":2,"area":null},{"id":"2407.15875","title":"Shapley Pruning for Neural Network Compression","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2510.15964","title":"Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2107.08382","title":"A High-Performance Adaptive Quantization Approach for Edge CNN Applications","created":"2021-07-18","cited_by_count":1,"area":null},{"id":"2110.08558","title":"Neural Network Pruning Through Constrained Reinforcement Learning","created":"2021-10-16","cited_by_count":1,"area":null},{"id":"2111.15179","title":"A Highly Effective Low-Rank Compression of Deep Neural Networks with Modified Beam-Search and Modified Stable Rank","created":"2021-11-30","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":"2204.01385","title":"Aligned Weight Regularizers for Pruning Pretrained Neural Networks","created":"2022-04-04","cited_by_count":1,"area":null},{"id":"2212.07547","title":"Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology","created":"2022-12-14","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":"2301.06193","title":"RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2301.11180","title":"Low-Rank Winograd Transformation for 3D Convolutional Neural Networks","created":"2023-01-26","cited_by_count":1,"area":null},{"id":"2303.11453","title":"Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing","created":"2023-03-20","cited_by_count":1,"area":null},{"id":"2310.20203","title":"Importance Estimation with Random Gradient for Neural Network Pruning","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2311.14323","title":"BinaryHPE: 3D Human Pose and Shape Estimation via Binarization","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2403.04805","title":"Pruning neural network models for gene regulatory dynamics using data and domain knowledge","created":"2024-03-05","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":"2510.20800","title":"Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2112.00698","title":"CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2205.02131","title":"Domino Saliency Metrics: Improving Existing Channel Saliency Metrics with Structural Information","created":"2022-05-04","cited_by_count":0,"area":null},{"id":"2206.10620","title":"CoCoPIE XGen: A Full-Stack AI-Oriented Optimizing Framework","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2211.08339","title":"Pruning Very Deep Neural Network Channels for Efficient Inference","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2306.13203","title":"Neural Network Pruning for Real-time Polyp Segmentation","created":"2023-06-22","cited_by_count":0,"area":null},{"id":"2307.07405","title":"Performance of $\\ell_1$ Regularization for Sparse Convex Optimization","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2402.08345","title":"Conditional Information Gain Trellis","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2512.06003","title":"PrunedCaps: A Case For Primary Capsules Discrimination","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2608.04811","title":"StaticSegFormer: An Efficient High-Performance Semantic Segmentation Based on Static Structured Pruning","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}