{"total":238,"rows":[{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128,"area":null},{"id":"2201.08135","title":"Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges","created":"2022-01-20","cited_by_count":84,"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":"2101.11714","title":"TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models","created":"2021-01-25","cited_by_count":58,"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":"2102.02416","title":"An end-to-end trainable hybrid classical-quantum classifier","created":"2021-02-04","cited_by_count":51,"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":"2302.09019","title":"Tensor Networks Meet Neural Networks: A Survey and Future Perspectives","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2401.14109","title":"CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks","created":"2024-01-25","cited_by_count":32,"area":null},{"id":"2106.02205","title":"Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators","created":"2021-06-04","cited_by_count":29,"area":null},{"id":"2406.06248","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","created":"2024-06-10","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":"2110.03861","title":"QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks","created":"2021-10-06","cited_by_count":27,"area":null},{"id":"2206.04804","title":"Theoretical Error Performance Analysis for Variational Quantum Circuit Based Functional Regression","created":"2022-06-08","cited_by_count":26,"area":null},{"id":"2406.18060","title":"AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning","created":"2024-06-26","cited_by_count":25,"area":null},{"id":"2104.12528","title":"Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks","created":"2021-04-26","cited_by_count":21,"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":"2107.08591","title":"Double Similarity Distillation for Semantic Image Segmentation","created":"2021-07-19","cited_by_count":19,"area":null},{"id":"2105.04554","title":"Local approximate Gaussian process regression for data-driven constitutive laws: Development and comparison with neural networks","created":"2021-05-07","cited_by_count":17,"area":null},{"id":"2303.11735","title":"Tensor networks for quantum machine learning","created":"2023-03-21","cited_by_count":17,"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":"2109.01545","title":"Large-Scale Learning with Fourier Features and Tensor Decompositions","created":"2021-09-03","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":"2408.01008","title":"Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs","created":"2024-08-02","cited_by_count":14,"area":null},{"id":"2103.06872","title":"Tensor networks and efficient descriptions of classical data","created":"2021-03-11","cited_by_count":13,"area":null},{"id":"2206.06597","title":"Permutation Search of Tensor Network Structures via Local Sampling","created":"2022-06-14","cited_by_count":13,"area":null},{"id":"2208.13141","title":"Federated Learning of Large Models at the Edge via Principal Sub-Model Training","created":"2022-08-28","cited_by_count":13,"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":"2304.12875","title":"Alternating Local Enumeration (TnALE): Solving Tensor Network Structure Search with Fewer Evaluations","created":"2023-04-25","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":"2410.13097","title":"Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models","created":"2024-10-16","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":"2401.10341","title":"ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks","created":"2024-01-18","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":"2503.05431","title":"Quantum-PEFT: Ultra parameter-efficient fine-tuning","created":"2025-03-07","cited_by_count":11,"area":null},{"id":"2601.21579","title":"KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices","created":"2026-01-29","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":"2203.06031","title":"Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing","created":"2022-03-11","cited_by_count":10,"area":null},{"id":"2303.13565","title":"Graph Tensor Networks: An Intuitive Framework for Designing Large-Scale Neural Learning Systems on Multiple Domains","created":"2023-03-23","cited_by_count":10,"area":null},{"id":"2406.01820","title":"Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning","created":"2024-06-03","cited_by_count":10,"area":null},{"id":"2106.08334","title":"Quantum-inspired event reconstruction with Tensor Networks: Matrix Product States","created":"2021-06-15","cited_by_count":9,"area":null},{"id":"2208.02235","title":"Quantum-Inspired Tensor Neural Networks for Partial Differential Equations","created":"2022-08-03","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":"2211.16749","title":"HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression","created":"2022-11-30","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":"2109.05736","title":"Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation","created":"2021-09-13","cited_by_count":8,"area":null},{"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":"2306.02697","title":"Efficient GPT Model Pre-training using Tensor Train Matrix Representation","created":"2023-06-05","cited_by_count":8,"area":null},{"id":"2310.14576","title":"Tensor Decomposition Based Attention Module for Spiking Neural Networks","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2401.02592","title":"Guaranteed Nonconvex Factorization Approach for Tensor Train Recovery","created":"2024-01-05","cited_by_count":8,"area":null},{"id":"2510.21599","title":"SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism","created":"2025-10-24","cited_by_count":8,"area":null},{"id":"2110.07631","title":"More Efficient Sampling for Tensor Decomposition With Worst-Case Guarantees","created":"2021-10-14","cited_by_count":7,"area":null},{"id":"2203.03366","title":"Improvements to Gradient Descent Methods for Quantum Tensor Network Machine Learning","created":"2022-03-03","cited_by_count":7,"area":null},{"id":"2206.11128","title":"tntorch: Tensor Network Learning with PyTorch","created":"2022-06-22","cited_by_count":7,"area":null},{"id":"2207.01751","title":"TT-PINN: A Tensor-Compressed Neural PDE Solver for Edge Computing","created":"2022-07-04","cited_by_count":7,"area":null},{"id":"2207.02851","title":"Tensor networks in machine learning","created":"2022-07-06","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":"2405.07735","title":"Federated Hierarchical Tensor Networks: a Collaborative Learning Quantum AI-Driven Framework for Healthcare","created":"2024-05-13","cited_by_count":7,"area":null},{"id":"2410.03496","title":"Fourier PINNs: From Strong Boundary Conditions to Adaptive Fourier Bases","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2410.17397","title":"Quantum Large Language Models via Tensor Network Disentanglers","created":"2024-10-22","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":"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":"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":"2505.21732","title":"LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2106.15666","title":"Probabilistic Graphical Models and Tensor Networks: A Hybrid Framework","created":"2021-06-29","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":"2310.11611","title":"In defense of parameter sharing for model-compression","created":"2023-10-17","cited_by_count":5,"area":null},{"id":"2401.16367","title":"TQCompressor: improving tensor decomposition methods in neural networks via permutations","created":"2024-01-29","cited_by_count":5,"area":null},{"id":"2402.02456","title":"tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2405.04590","title":"Language Modeling Using Tensor Trains","created":"2024-05-07","cited_by_count":5,"area":null},{"id":"2411.05873","title":"Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approach","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2502.06916","title":"QuIC: Quantum-Inspired Compound Adapters for Parameter Efficient Fine-Tuning","created":"2025-02-10","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":"2105.13890","title":"Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization","created":"2021-05-27","cited_by_count":4,"area":null},{"id":"2105.14250","title":"Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation","created":"2021-05-29","cited_by_count":4,"area":null},{"id":"2106.04741","title":"Marginalizable Density Models","created":"2021-06-08","cited_by_count":4,"area":null},{"id":"2302.11883","title":"PIFON-EPT: MR-Based Electrical Property Tomography Using Physics-Informed Fourier Networks","created":"2023-02-23","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":"2410.12607","title":"Low-Rank Adversarial PGD Attack","created":"2024-10-16","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":"2506.16032","title":"A Scalable Factorization Approach for High-Order Structured Tensor Recovery","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2101.00245","title":"The Bayesian Method of Tensor Networks","created":"2021-01-01","cited_by_count":3,"area":null},{"id":"2102.06900","title":"Segmenting two-dimensional structures with strided tensor networks","created":"2021-02-13","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":"2107.04380","title":"Model compression as constrained optimization, with application to neural nets. Part V: combining compressions","created":"2021-07-09","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":"2109.15200","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}],"next_cursor":"100"}