{"total":203,"rows":[{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259,"area":"distill"},{"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":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141,"area":null},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133,"area":null},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128,"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":"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":"2103.05861","title":"Manifold Regularized Dynamic Network Pruning","created":"2021-03-10","cited_by_count":43,"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":"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":"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":"2111.14655","title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2104.02244","title":"Content-Aware GAN Compression","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28,"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":"2203.04940","title":"Data-Efficient Structured Pruning via Submodular Optimization","created":"2022-03-09","cited_by_count":23,"area":null},{"id":"2103.17267","title":"Bit-Mixer: Mixed-precision networks with runtime bit-width selection","created":"2021-03-31","cited_by_count":22,"area":null},{"id":"2301.11233","title":"BiBench: Benchmarking and Analyzing Network Binarization","created":"2023-01-26","cited_by_count":22,"area":null},{"id":"2110.14807","title":"L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization","created":"2021-10-27","cited_by_count":21,"area":null},{"id":"2402.01799","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","created":"2024-02-02","cited_by_count":21,"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":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19,"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":"2205.10036","title":"Exploring Extreme Parameter Compression for Pre-trained Language Models","created":"2022-05-20","cited_by_count":15,"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":"2202.00441","title":"Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction","created":"2022-02-01","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":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2111.06705","title":"A compact butterfly-style silicon photonic-electronic neural chip for hardware-efficient deep learning","created":"2021-11-11","cited_by_count":13,"area":null},{"id":"2209.14624","title":"Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning","created":"2022-09-29","cited_by_count":13,"area":null},{"id":"2109.05221","title":"Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence","created":"2021-09-11","cited_by_count":12,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","cited_by_count":12,"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":"2506.17093","title":"Identifiability of Deep Polynomial Neural Networks","created":"2025-06-20","cited_by_count":12,"area":null},{"id":"2106.07751","title":"FedNILM: Applying Federated Learning to NILM Applications at the Edge","created":"2021-06-07","cited_by_count":11,"area":null},{"id":"2406.10019","title":"Group and Shuffle: Efficient Structured Orthogonal Parametrization","created":"2024-06-14","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":"2108.00065","title":"Model Preserving Compression for Neural Networks","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2510.03358","title":"Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility","created":"2025-10-02","cited_by_count":9,"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":"2304.10891","title":"Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2107.00090","title":"Mesh-based graph convolutional neural networks for modeling materials with microstructure","created":"2021-06-04","cited_by_count":7,"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":"2209.15529","title":"TT-NF: Tensor Train Neural Fields","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2406.17887","title":"Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees","created":"2024-06-25","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":"2103.04217","title":"Spectral Tensor Train Parameterization of Deep Learning Layers","created":"2021-03-07","cited_by_count":6,"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":"2104.05048","title":"Rank-R FNN: A Tensor-Based Learning Model for High-Order Data Classification","created":"2021-04-11","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":"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":"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":"2505.08022","title":"Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks","created":"2025-05-12","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":"2112.11438","title":"Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":5,"area":null},{"id":"2209.11064","title":"Deep Learning on Home Drone: Searching for the Optimal Architecture","created":"2022-09-21","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":"2306.08595","title":"TensorKrowch: Smooth integration of tensor networks in machine learning","created":"2023-06-14","cited_by_count":5,"area":null},{"id":"2406.17261","title":"TRAWL: Tensor Reduced and Approximated Weights for Large Language Models","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2411.18065","title":"FlexiBit: Fully Flexible Precision Bit-parallel Accelerator Architecture for Arbitrary Mixed Precision AI","created":"2024-11-27","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":"2207.12773","title":"Quiver neural networks","created":"2022-07-26","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":"2405.06626","title":"Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models","created":"2024-05-10","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":"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":"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":"2105.06250","title":"3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration","created":"2021-05-11","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":"2204.05566","title":"Compact Model Training by Low-Rank Projection with Energy Transfer","created":"2022-04-12","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":"2205.15437","title":"AMED: Automatic Mixed-Precision Quantization for Edge Devices","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2206.01509","title":"Canonical convolutional neural networks","created":"2022-06-03","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":"2301.11650","title":"Fast Region of Interest Proposals on Maritime UAVs","created":"2023-01-27","cited_by_count":3,"area":null},{"id":"2303.16214","title":"Tetra-AML: Automatic Machine Learning via Tensor Networks","created":"2023-03-28","cited_by_count":3,"area":null},{"id":"2308.04672","title":"Resource Constrained Model Compression via Minimax Optimization for Spiking Neural Networks","created":"2023-08-09","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}],"next_cursor":"100"}