{"total":162,"rows":[{"id":"2312.05821","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","created":"2023-12-10","cited_by_count":169,"area":"inference"},{"id":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"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":"2502.04959","title":"No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces","created":"2025-02-07","cited_by_count":96,"area":null},{"id":"2310.00120","title":"Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs","created":"2023-09-29","cited_by_count":68,"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":"2107.03436","title":"Tensor Methods in Computer Vision and Deep Learning","created":"2021-07-07","cited_by_count":52,"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":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2205.13571","title":"Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations","created":"2022-05-26","cited_by_count":43,"area":null},{"id":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2105.11228","title":"Towards Compact CNNs via Collaborative Compression","created":"2021-05-24","cited_by_count":36,"area":null},{"id":"2103.08756","title":"Revisiting Dynamic Convolution via Matrix Decomposition","created":"2021-03-15","cited_by_count":35,"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":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2302.09019","title":"Tensor Networks Meet Neural Networks: A Survey and Future Perspectives","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2110.12661","title":"ZerO Initialization: Initializing Neural Networks with only Zeros and Ones","created":"2021-10-25","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":"2112.09852","title":"LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision","created":"2021-12-18","cited_by_count":20,"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":"2301.09422","title":"HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks","created":"2023-01-20","cited_by_count":20,"area":null},{"id":"2104.11138","title":"NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy","created":"2021-04-22","cited_by_count":16,"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":"2405.14377","title":"CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2106.09309","title":"Layer Folding: Neural Network Depth Reduction using Activation Linearization","created":"2021-06-17","cited_by_count":14,"area":null},{"id":"2109.14710","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","created":"2021-09-29","cited_by_count":14,"area":null},{"id":"2304.13539","title":"Tensor Decomposition for Model Reduction in Neural Networks: A Review","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2305.17235","title":"COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision Models","created":"2023-05-26","cited_by_count":14,"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":"2305.19059","title":"Geometry-aware training of factorized layers in tensor Tucker format","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2402.11417","title":"LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models","created":"2024-02-18","cited_by_count":12,"area":null},{"id":"2203.15751","title":"A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification","created":"2022-03-29","cited_by_count":11,"area":null},{"id":"2401.10341","title":"ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2107.04386","title":"Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression","created":"2021-07-09","cited_by_count":10,"area":null},{"id":"2301.05345","title":"GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer","created":"2023-01-13","cited_by_count":10,"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":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2211.13771","title":"Towards Practical Control of Singular Values of Convolutional Layers","created":"2022-11-24","cited_by_count":9,"area":null},{"id":"2104.05758","title":"Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2106.10885","title":"Knowledge Distillation via Instance-level Sequence Learning","created":"2021-06-21","cited_by_count":8,"area":"distill"},{"id":"2203.13556","title":"Deformable Butterfly: A Highly Structured and Sparse Linear Transform","created":"2022-03-25","cited_by_count":8,"area":null},{"id":"2205.15307","title":"A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks","created":"2022-05-28","cited_by_count":8,"area":null},{"id":"2208.03934","title":"Inflating 2D Convolution Weights for Efficient Generation of 3D Medical Images","created":"2022-08-08","cited_by_count":8,"area":null},{"id":"2302.03886","title":"Approximately Optimal Core Shapes for Tensor Decompositions","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2311.05739","title":"Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency","created":"2023-11-09","cited_by_count":8,"area":null},{"id":"2506.20353","title":"DipSVD: Dual-importance Protected SVD for Efficient LLM Compression","created":"2025-06-25","cited_by_count":8,"area":null},{"id":"2203.12314","title":"Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices","created":"2022-03-23","cited_by_count":7,"area":null},{"id":"2502.10216","title":"Forget the Data and Fine-Tuning! Just Fold the Network to Compress","created":"2025-02-14","cited_by_count":7,"area":null},{"id":"2103.10858","title":"Toward Compact Deep Neural Networks via Energy-Aware Pruning","created":"2021-03-19","cited_by_count":6,"area":null},{"id":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2105.04983","title":"Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecasting","created":"2021-05-11","cited_by_count":6,"area":null},{"id":"2106.05997","title":"Verifying Quantized Neural Networks using SMT-Based Model Checking","created":"2021-06-10","cited_by_count":6,"area":null},{"id":"2112.03690","title":"Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization","created":"2021-12-07","cited_by_count":6,"area":null},{"id":"2203.04516","title":"Update Compression for Deep Neural Networks on the Edge","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2308.04595","title":"Quantization Aware Factorization for Deep Neural Network Compression","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2411.06346","title":"Activation Map Compression through Tensor Decomposition for Deep Learning","created":"2024-11-10","cited_by_count":6,"area":null},{"id":"2501.02379","title":"TensorGRaD: Tensor Gradient Robust Decomposition for Memory-Efficient Neural Operator Training","created":"2025-01-04","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":"2101.02268","title":"LightLayers: Parameter Efficient Dense and Convolutional Layers for Image Classification","created":"2021-01-06","cited_by_count":4,"area":null},{"id":"2101.04073","title":"Deeplite Neutrino: An End-to-End Framework for Constrained Deep Learning Model Optimization","created":"2021-01-11","cited_by_count":4,"area":null},{"id":"2106.04741","title":"Marginalizable Density Models","created":"2021-06-08","cited_by_count":4,"area":null},{"id":"2107.05298","title":"HEMP: High-order Entropy Minimization for neural network comPression","created":"2021-07-12","cited_by_count":4,"area":null},{"id":"2110.09674","title":"Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation","created":"2021-10-19","cited_by_count":4,"area":"distill"},{"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":"2309.06047","title":"Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2410.02147","title":"Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2412.06868","title":"Compression for Better: A General and Stable Lossless Compression Framework","created":"2024-12-09","cited_by_count":4,"area":null},{"id":"2505.20132","title":"Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2506.09105","title":"MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2507.04792","title":"Model Compression using Progressive Channel Pruning","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2602.18116","title":"Cut Less, Fold More: Model Compression through the Lens of Projection Geometry","created":"2026-02-20","cited_by_count":4,"area":null},{"id":"2104.09056","title":"RingCNN: Exploiting Algebraically-Sparse Ring Tensors for Energy-Efficient CNN-Based Computational Imaging","created":"2021-04-19","cited_by_count":3,"area":null},{"id":"2108.04029","title":"Tensor Yard: One-Shot Algorithm of Hardware-Friendly Tensor-Train Decomposition for Convolutional Neural Networks","created":"2021-08-09","cited_by_count":3,"area":null},{"id":"2109.09310","title":"Learning Versatile Convolution Filters for Efficient Visual Recognition","created":"2021-09-20","cited_by_count":3,"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":"2203.02617","title":"How to Train Unstable Looped Tensor Network","created":"2022-03-05","cited_by_count":3,"area":null},{"id":"2205.12961","title":"Position: Tensor Networks are a Valuable Asset for Green AI","created":"2022-05-25","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":"2208.10404","title":"SVD-NAS: Coupling Low-Rank Approximation and Neural Architecture Search","created":"2022-08-22","cited_by_count":3,"area":null},{"id":"2311.03912","title":"FLORA: Fine-grained Low-Rank Architecture Search for Vision Transformer","created":"2023-11-07","cited_by_count":3,"area":null},{"id":"2409.17085","title":"Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2411.15086","title":"Quantum-enhanced unsupervised image segmentation for medical images analysis","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2412.06867","title":"Lossless Model Compression via Joint Low-Rank Factorization Optimization","created":"2024-12-09","cited_by_count":3,"area":null},{"id":"2501.06663","title":"Ultra Memory-Efficient On-FPGA Training of Transformers via Tensor-Compressed Optimization","created":"2025-01-11","cited_by_count":3,"area":null},{"id":"2103.10047","title":"Similarity Transfer for Knowledge Distillation","created":"2021-03-18","cited_by_count":2,"area":"distill"},{"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":"2109.04022","title":"Multi-Tensor Network Representation for High-Order Tensor Completion","created":"2021-09-09","cited_by_count":2,"area":null},{"id":"2203.07033","title":"Compressing CNN Kernels for Videos Using Tucker Decompositions: Towards Lightweight CNN Applications","created":"2022-03-10","cited_by_count":2,"area":null},{"id":"2301.00314","title":"Causal Deep Learning","created":"2023-01-01","cited_by_count":2,"area":null},{"id":"2305.05318","title":"How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?","created":"2023-05-09","cited_by_count":2,"area":null},{"id":"2308.13898","title":"Memory-aware Scheduling for Complex Wired Networks with Iterative Graph Optimization","created":"2023-08-26","cited_by_count":2,"area":null},{"id":"2309.01077","title":"Robust Adversarial Defense by Tensor Factorization","created":"2023-09-03","cited_by_count":2,"area":null},{"id":"2401.01373","title":"Boosting Defect Detection in Manufacturing using Tensor Convolutional Neural Networks","created":"2023-12-29","cited_by_count":2,"area":null},{"id":"2403.14379","title":"Tensor network compressibility of convolutional models","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2102.03494","title":"FFConv: Fast Factorized Convolutional Neural Network Inference on Encrypted Data","created":"2021-02-06","cited_by_count":1,"area":null},{"id":"2105.04218","title":"Exploiting Elasticity in Tensor Ranks for Compressing Neural Networks","created":"2021-05-10","cited_by_count":1,"area":null},{"id":"2108.11441","title":"Design and Scaffolded Training of an Efficient DNN Operator for Computer Vision on the Edge","created":"2021-08-25","cited_by_count":1,"area":null}],"next_cursor":"100"}