{"total":281,"rows":[{"id":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256,"area":null},{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212,"area":null},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195,"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":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"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":"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":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84,"area":null},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79,"area":null},{"id":"2307.02129","title":"How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model","created":"2023-07-05","cited_by_count":71,"area":null},{"id":"2210.05337","title":"SGD with Large Step Sizes Learns Sparse Features","created":"2022-10-11","cited_by_count":68,"area":null},{"id":"2211.16386","title":"Compressing Volumetric Radiance Fields to 1 MB","created":"2022-11-29","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":"2110.06554","title":"Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization","created":"2021-10-13","cited_by_count":61,"area":null},{"id":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"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":"2206.06122","title":"Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning","created":"2022-06-13","cited_by_count":50,"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":"2103.08756","title":"Revisiting Dynamic Convolution via Matrix Decomposition","created":"2021-03-15","cited_by_count":35,"area":null},{"id":"2209.14635","title":"Compressed Gastric Image Generation Based on Soft-Label Dataset Distillation for Medical Data Sharing","created":"2022-09-29","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":"2106.06091","title":"DECORE: Deep Compression with Reinforcement Learning","created":"2021-06-11","cited_by_count":29,"area":null},{"id":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28,"area":null},{"id":"2110.14439","title":"Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme","created":"2021-10-27","cited_by_count":23,"area":null},{"id":"2203.04940","title":"Data-Efficient Structured Pruning via Submodular Optimization","created":"2022-03-09","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":"2102.07156","title":"ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations","created":"2021-02-14","cited_by_count":21,"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":"2302.03213","title":"LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup","created":"2023-02-07","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":"2206.05794","title":"SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network","created":"2022-06-12","cited_by_count":19,"area":null},{"id":"2305.18512","title":"A Rainbow in Deep Network Black Boxes","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2312.14229","title":"Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2101.07985","title":"Network Pruning using Adaptive Exemplar Filters","created":"2021-01-20","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":"2201.03297","title":"GhostNets on Heterogeneous Devices via Cheap Operations","created":"2022-01-10","cited_by_count":15,"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":"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":"2109.14710","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","created":"2021-09-29","cited_by_count":14,"area":null},{"id":"2206.04662","title":"DiSparse: Disentangled Sparsification for Multitask Model Compression","created":"2022-06-09","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":"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":"2203.10135","title":"Learning Compressed Embeddings for On-Device Inference","created":"2022-03-18","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":"2209.14826","title":"Towards Lightweight Black-Box Attacks against Deep Neural Networks","created":"2022-09-29","cited_by_count":13,"area":null},{"id":"2111.07964","title":"Deep Network Approximation in Terms of Intrinsic Parameters","created":"2021-11-15","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":"2108.02720","title":"Generalizable Mixed-Precision Quantization via Attribution Rank Preservation","created":"2021-08-05","cited_by_count":11,"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":"2105.14070","title":"Accelerating Neural ODEs Using Model Order Reduction","created":"2021-05-28","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":"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":"2402.04051","title":"Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods","created":"2024-02-06","cited_by_count":9,"area":null},{"id":"2407.10542","title":"3D Geometric Shape Assembly via Efficient Point Cloud Matching","created":"2024-07-15","cited_by_count":9,"area":null},{"id":"2503.19859","title":"An Overview of Low-Rank Structures in the Training and Adaptation of Large Models","created":"2025-03-25","cited_by_count":9,"area":null},{"id":"2503.22178","title":"AdaRank: Adaptive Rank Pruning for Enhanced Model Merging","created":"2025-03-28","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":"2502.17788","title":"On-device edge learning for IoT data streams: a survey","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","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":"2104.14696","title":"Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer","created":"2021-04-29","cited_by_count":7,"area":null},{"id":"2202.12400","title":"The rise of the lottery heroes: why zero-shot pruning is hard","created":"2022-02-24","cited_by_count":7,"area":null},{"id":"2206.09149","title":"Piecewise Linear Neural Networks and Deep Learning","created":"2022-06-18","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":"2604.02119","title":"AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression","created":"2026-04-02","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":"2105.01867","title":"A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2112.02834","title":"A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics","created":"2021-12-06","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":"2304.05440","title":"PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2306.02090","title":"Deep Classifier Mimicry without Data Access","created":"2023-06-03","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":"2509.22075","title":"CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2207.07268","title":"Lightweight Vision Transformer with Cross Feature Attention","created":"2022-07-15","cited_by_count":5,"area":null},{"id":"2211.09949","title":"Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers","created":"2022-11-17","cited_by_count":5,"area":null},{"id":"2303.09736","title":"Dynamic Structure Pruning for Compressing CNNs","created":"2023-03-17","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":"2304.00891","title":"Online Algorithms for Hierarchical Inference in Deep Learning applications at the Edge","created":"2023-04-03","cited_by_count":5,"area":null},{"id":"2304.02319","title":"Efficient CNNs via Passive Filter Pruning","created":"2023-04-05","cited_by_count":5,"area":null},{"id":"2306.04147","title":"CFDP: Common Frequency Domain Pruning","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2310.05166","title":"A Corrected Expected Improvement Acquisition Function Under Noisy Observations","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2405.20876","title":"Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2503.16916","title":"Temporal Action Detection Model Compression by Progressive Block Drop","created":"2025-03-21","cited_by_count":5,"area":null}],"next_cursor":"100"}