{"total":109,"rows":[{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2110.06554","title":"Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization","created":"2021-10-13","cited_by_count":61,"area":null},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50,"area":null},{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2106.10197","title":"A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents","created":"2021-06-18","cited_by_count":42,"area":null},{"id":"2205.05675","title":"NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results","created":"2022-05-11","cited_by_count":40,"area":null},{"id":"2102.10462","title":"BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization","created":"2021-02-20","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2105.11228","title":"Towards Compact CNNs via Collaborative Compression","created":"2021-05-24","cited_by_count":36,"area":null},{"id":"2410.10912","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","created":"2024-10-14","cited_by_count":36,"area":null},{"id":"2107.11442","title":"Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition","created":"2021-07-23","cited_by_count":33,"area":null},{"id":"2104.11487","title":"Skip-Convolutions for Efficient Video Processing","created":"2021-04-23","cited_by_count":32,"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":"2202.03038","title":"Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry","created":"2022-02-07","cited_by_count":28,"area":null},{"id":"2203.04940","title":"Data-Efficient Structured Pruning via Submodular Optimization","created":"2022-03-09","cited_by_count":23,"area":null},{"id":"2505.11497","title":"QVGen: Pushing the Limit of Quantized Video Generative Models","created":"2025-05-16","cited_by_count":22,"area":"diffusion"},{"id":"2102.06841","title":"Collaborative Intelligence: Challenges and Opportunities","created":"2021-02-13","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":"2104.05706","title":"Towards Efficient Graph Convolutional Networks for Point Cloud Handling","created":"2021-04-12","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":"2102.10301","title":"Towards Accurate and Compact Architectures via Neural Architecture Transformer","created":"2021-02-20","cited_by_count":17,"area":null},{"id":"2209.08498","title":"LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF","created":"2022-09-18","cited_by_count":17,"area":null},{"id":"2205.11921","title":"Compression-aware Training of Neural Networks using Frank-Wolfe","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2110.11650","title":"Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation","created":"2021-10-22","cited_by_count":15,"area":null},{"id":"2110.01606","title":"Breast Cancer Diagnosis in Two-View Mammography Using End-to-End Trained EfficientNet-Based Convolutional Network","created":"2021-10-01","cited_by_count":13,"area":null},{"id":"2209.14826","title":"Towards Lightweight Black-Box Attacks against Deep Neural Networks","created":"2022-09-29","cited_by_count":13,"area":null},{"id":"2203.03610","title":"ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretization","created":"2022-03-07","cited_by_count":10,"area":null},{"id":"2203.09594","title":"Delta Distillation for Efficient Video Processing","created":"2022-03-17","cited_by_count":10,"area":"distill"},{"id":"2105.14070","title":"Accelerating Neural ODEs Using Model Order Reduction","created":"2021-05-28","cited_by_count":9,"area":null},{"id":"2106.08746","title":"Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses","created":"2021-06-16","cited_by_count":9,"area":null},{"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":"2108.00065","title":"Model Preserving Compression for Neural Networks","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2310.10700","title":"PELA: Learning Parameter-Efficient Models with Low-Rank Approximation","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2210.07745","title":"Confidence estimation of classification based on the distribution of the neural network output layer","created":"2022-10-14","cited_by_count":8,"area":null},{"id":"2312.06273","title":"Regroup Median Loss for Combating Label Noise","created":"2023-12-11","cited_by_count":8,"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":"2402.00084","title":"EPSD: Early Pruning with Self-Distillation for Efficient Model Compression","created":"2024-01-31","cited_by_count":6,"area":"distill"},{"id":"2411.06346","title":"Activation Map Compression through Tensor Decomposition for Deep Learning","created":"2024-11-10","cited_by_count":6,"area":null},{"id":"2505.21732","title":"LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing","created":"2025-05-27","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":"2208.10608","title":"RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN","created":"2022-08-22","cited_by_count":4,"area":null},{"id":"2212.01957","title":"CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness","created":"2022-12-04","cited_by_count":4,"area":null},{"id":"2309.17211","title":"Data-Free Dynamic Compression of CNNs for Tractable Efficiency","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2109.15200","title":"Semi-tensor Product-based TensorDecomposition for Neural Network Compression","created":"2021-09-30","cited_by_count":3,"area":null},{"id":"2202.00834","title":"Nonlinear Initialization Methods for Low-Rank Neural Networks","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2203.02617","title":"How to Train Unstable Looped Tensor Network","created":"2022-03-05","cited_by_count":3,"area":null},{"id":"2203.11323","title":"Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2204.05566","title":"Compact Model Training by Low-Rank Projection with Energy Transfer","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2207.11048","title":"Quantized Sparse Weight Decomposition for Neural Network Compression","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2208.06660","title":"Entropy Induced Pruning Framework for Convolutional Neural Networks","created":"2022-08-13","cited_by_count":3,"area":null},{"id":"2208.10404","title":"SVD-NAS: Coupling Low-Rank Approximation and Neural Architecture Search","created":"2022-08-22","cited_by_count":3,"area":null},{"id":"2308.00759","title":"Decomposition Ascribed Synergistic Learning for Unified Image Restoration","created":"2023-08-01","cited_by_count":3,"area":null},{"id":"2308.07641","title":"Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping","created":"2023-08-15","cited_by_count":3,"area":null},{"id":"2404.08079","title":"DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models","created":"2024-04-11","cited_by_count":3,"area":null},{"id":"2501.07396","title":"Zero-Shot Scene Understanding for Automatic Target Recognition Using Large Vision-Language Models","created":"2025-01-13","cited_by_count":3,"area":"mllm"},{"id":"2502.02766","title":"Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2107.04220","title":"Deep Learning models for benign and malign Ocular Tumor Growth Estimation","created":"2021-07-09","cited_by_count":2,"area":null},{"id":"2108.13055","title":"Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2110.09163","title":"A Dimensionality Reduction Approach for Convolutional Neural Networks","created":"2021-10-18","cited_by_count":2,"area":null},{"id":"2305.12458","title":"Infor-Coef: Information Bottleneck-based Dynamic Token Downsampling for Compact and Efficient language model","created":"2023-05-21","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":"2308.09511","title":"ResQ: Residual Quantization for Video Perception","created":"2023-08-18","cited_by_count":2,"area":null},{"id":"2405.13039","title":"Surgical Feature-Space Decomposition of LLMs: Why, When and How?","created":"2024-05-17","cited_by_count":2,"area":null},{"id":"2506.02393","title":"RRCANet: Recurrent Reusable-Convolution Attention Network for Infrared Small Target Detection","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2509.25136","title":"BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2101.06608","title":"Network Automatic Pruning: Start NAP and Take a Nap","created":"2021-01-17","cited_by_count":1,"area":null},{"id":"2106.02552","title":"Active Covering","created":"2021-06-04","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":"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":"2208.14046","title":"A Deep Neural Networks ensemble workflow from hyperparameter search to inference leveraging GPU clusters","created":"2022-08-30","cited_by_count":1,"area":null},{"id":"2306.01359","title":"DWT-CompCNN: Deep Image Classification Network for High Throughput JPEG 2000 Compressed Documents","created":"2023-06-02","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":"2405.15877","title":"Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2602.09509","title":"Beyond Student: An Asymmetric Network for Neural Network Inheritance","created":"2026-02-10","cited_by_count":1,"area":"distill"},{"id":"2606.01412","title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2101.11376","title":"Learning Abstract Representations through Lossy Compression of Multi-Modal Signals","created":"2021-01-27","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":"2110.08679","title":"An Acceleration Method Based on Deep Learning and Multilinear Feature Space","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2110.15644","title":"Gabor filter incorporated CNN for compression","created":"2021-10-29","cited_by_count":0,"area":null},{"id":"2112.13551","title":"Learning Robust and Lightweight Model through Separable Structured Transformations","created":"2021-12-27","cited_by_count":0,"area":null},{"id":"2203.06465","title":"Towards On-Device AI and Blockchain for 6G enabled Agricultural Supply-chain Management","created":"2022-03-12","cited_by_count":0,"area":null},{"id":"2206.10155","title":"Review Neural Networks about Image Transformation Based on IGC Learning Framework with Annotated Information","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2210.06299","title":"SeKron: A Decomposition Method Supporting Many Factorization Structures","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2210.08951","title":"Approximating Continuous Convolutions for Deep Network Compression","created":"2022-10-17","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":"2304.11706","title":"Deep Convolutional Tables: Deep Learning without Convolutions","created":"2023-04-23","cited_by_count":0,"area":null},{"id":"2306.15390","title":"DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2310.12461","title":"Balanced Group Convolution: An Improved Group Convolution Based on Approximability Estimates","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2401.08014","title":"Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2403.00606","title":"Flattening Singular Values of Factorized Convolution for Medical Images","created":"2024-03-01","cited_by_count":0,"area":null},{"id":"2403.10558","title":"Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attack","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2403.11631","title":"Compositional Kronecker Context Optimization for Vision-Language Models","created":"2024-03-18","cited_by_count":0,"area":"mllm"},{"id":"2404.04734","title":"Towards Generalized Entropic Sparsification for Convolutional Neural Networks","created":"2024-04-06","cited_by_count":0,"area":null},{"id":"2406.09315","title":"Vertical LoRA: Dense Expectation-Maximization Interpretation of Transformers","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2408.00923","title":"Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2412.16886","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","created":"2024-12-22","cited_by_count":0,"area":null},{"id":"2506.04555","title":"Enhancing Frequency for Single Image Super-Resolution with Learnable Separable Kernels","created":"2025-06-05","cited_by_count":0,"area":null}],"next_cursor":"100"}