{"total":96,"rows":[{"id":"2103.03123","title":"COIN: COmpression with Implicit Neural representations","created":"2021-03-03","cited_by_count":233,"area":null},{"id":"2103.10559","title":"CDFI: Compression-Driven Network Design for Frame Interpolation","created":"2021-03-18","cited_by_count":56,"area":null},{"id":"2503.06027","title":"Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models","created":"2025-03-08","cited_by_count":46,"area":null},{"id":"2104.09987","title":"Differentiable Model Compression via Pseudo Quantization Noise","created":"2021-04-20","cited_by_count":45,"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":"2108.12659","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","created":"2021-08-28","cited_by_count":31,"area":null},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25,"area":null},{"id":"2208.04425","title":"Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints","created":"2022-08-08","cited_by_count":25,"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":"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":"2309.10285","title":"Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity","created":"2023-09-19","cited_by_count":17,"area":null},{"id":"2203.07808","title":"Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs","created":"2022-03-15","cited_by_count":16,"area":null},{"id":"2112.00914","title":"HyperSPNs: Compact and Expressive Probabilistic Circuits","created":"2021-12-02","cited_by_count":14,"area":null},{"id":"2407.11033","title":"Hadamard Adapter: An Extreme Parameter-Efficient Adapter Tuning Method for Pre-trained Language Models","created":"2024-07-04","cited_by_count":13,"area":null},{"id":"2102.03773","title":"SeReNe: Sensitivity based Regularization of Neurons for Structured Sparsity in Neural Networks","created":"2021-02-07","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":"2207.04895","title":"Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility","created":"2022-07-11","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":"2106.06882","title":"Sparse PointPillars: Maintaining and Exploiting Input Sparsity to Improve Runtime on Embedded Systems","created":"2021-06-12","cited_by_count":11,"area":null},{"id":"2109.10795","title":"Neural network relief: a pruning algorithm based on neural activity","created":"2021-09-22","cited_by_count":10,"area":null},{"id":"2112.15139","title":"Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural Networks","created":"2021-12-30","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":"2407.00928","title":"FoldGPT: Simple and Effective Large Language Model Compression Scheme","created":"2024-07-01","cited_by_count":9,"area":null},{"id":"2301.08292","title":"Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superposition","created":"2023-01-19","cited_by_count":8,"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":"2203.14645","title":"REx: Data-Free Residual Quantization Error Expansion","created":"2022-03-28","cited_by_count":6,"area":null},{"id":"2209.04551","title":"Sparsity-guided Network Design for Frame Interpolation","created":"2022-09-09","cited_by_count":6,"area":null},{"id":"2509.22445","title":"Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2202.04629","title":"Reducing Redundancy in the Bottleneck Representation of the Autoencoders","created":"2022-02-09","cited_by_count":5,"area":null},{"id":"2209.14252","title":"Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networks","created":"2022-09-28","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":"2104.10544","title":"Lossless Compression with Latent Variable Models","created":"2021-04-21","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":"2201.05020","title":"Automatic Sparse Connectivity Learning for Neural Networks","created":"2022-01-13","cited_by_count":4,"area":null},{"id":"2308.04269","title":"Lossy and Lossless (L$^2$) Post-training Model Size Compression","created":"2023-08-08","cited_by_count":4,"area":null},{"id":"2309.00964","title":"eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models","created":"2023-09-02","cited_by_count":4,"area":null},{"id":"2404.10824","title":"Decoupled Weight Decay for Any $p$ Norm","created":"2024-04-16","cited_by_count":4,"area":null},{"id":"2406.19301","title":"MCNC: Manifold-Constrained Reparameterization for Neural Compression","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2102.11893","title":"Honey, I Shrunk The Actor: A Case Study on Preserving Performance with Smaller Actors in Actor-Critic RL","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2204.04977","title":"Regularization-based Pruning of Irrelevant Weights in Deep Neural Architectures","created":"2022-04-11","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":"2301.13330","title":"Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2306.09380","title":"Understanding Parameter Sharing in Transformers","created":"2023-06-15","cited_by_count":3,"area":null},{"id":"2102.02804","title":"A Deeper Look into Convolutions via Eigenvalue-based Pruning","created":"2021-02-04","cited_by_count":2,"area":null},{"id":"2311.03096","title":"Weight-Sharing Regularization","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2503.14799","title":"Pruning-Based TinyML Optimization of Machine Learning Models for Anomaly Detection in Electric Vehicle Charging Infrastructure","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2505.17856","title":"Stochastic Weight Sharing for Bayesian Neural Networks","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2505.23337","title":"Matryoshka Model Learning for Improved Elastic Student Models","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2507.03504","title":"Information-Bottleneck Driven Binary Neural Network for Change Detection","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2509.13662","title":"Deep Lookup Network","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2512.20814","title":"FedMPDD: Communication-Efficient Federated Learning with Privacy Preservation Attributes via Projected Directional Derivative","created":"2025-12-23","cited_by_count":2,"area":null},{"id":"2602.14896","title":"Algorithmic Simplification of Neural Networks with Mosaic-of-Motifs","created":"2026-02-16","cited_by_count":2,"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":"2111.02018","title":"Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention","created":"2021-11-03","cited_by_count":1,"area":null},{"id":"2201.00063","title":"Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systems","created":"2021-12-31","cited_by_count":1,"area":null},{"id":"2206.08464","title":"PRANC: Pseudo RAndom Networks for Compacting deep models","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2210.13554","title":"Weight Fixing Networks","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2212.12921","title":"Learning k-Level Structured Sparse Neural Networks Using Group Envelope Regularization","created":"2022-12-25","cited_by_count":1,"area":null},{"id":"2309.13575","title":"Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantization","created":"2023-09-24","cited_by_count":1,"area":null},{"id":"2312.03038","title":"Sample-based Dynamic Hierarchical Transformer with Layer and Head Flexibility via Contextual Bandit","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2502.02448","title":"Sparse Data Diffusion for Scientific Simulations in Biology and Physics","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2503.20454","title":"Lipschitz Constant Meets Condition Number: Learning Robust and Compact Deep Neural Networks","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2505.17469","title":"Efficient compression of neural networks and datasets","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2505.24413","title":"Multi-task Learning for Heterogeneous Multi-source Block-Wise Missing Data","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2506.07975","title":"Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2510.20800","title":"Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2512.06288","title":"Theoretical Compression Bounds for Wide Multilayer Perceptrons","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2603.18423","title":"SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2103.10629","title":"Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2108.06626","title":"A Survey on GAN Acceleration Using Memory Compression Technique","created":"2021-08-14","cited_by_count":0,"area":null},{"id":"2110.05954","title":"Mining the Weights Knowledge for Optimizing Neural Network Structures","created":"2021-10-11","cited_by_count":0,"area":null},{"id":"2201.06376","title":"UWC: Unit-wise Calibration Towards Rapid Network Compression","created":"2022-01-17","cited_by_count":0,"area":null},{"id":"2202.05137","title":"Quantization in Layer's Input is Matter","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2204.01935","title":"Nonlocal optimization of binary neural networks","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2205.01508","title":"Compact Neural Networks via Stacking Designed Basic Units","created":"2022-05-03","cited_by_count":0,"area":null},{"id":"2207.10083","title":"Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss","created":"2022-07-20","cited_by_count":0,"area":null},{"id":"2210.13468","title":"Fast and Low-Memory Deep Neural Networks Using Binary Matrix Factorization","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2211.11308","title":"Novel transfer learning schemes based on Siamese networks and synthetic data","created":"2022-11-21","cited_by_count":0,"area":null},{"id":"2301.06641","title":"Scaling Deep Networks with the Mesh Adaptive Direct Search algorithm","created":"2023-01-17","cited_by_count":0,"area":null},{"id":"2304.08411","title":"Evil from Within: Machine Learning Backdoors through Hardware Trojans","created":"2023-04-17","cited_by_count":0,"area":null},{"id":"2305.18789","title":"Generalization Bounds for Magnitude-Based Pruning via Sparse Matrix Sketching","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2306.17442","title":"Designing strong baselines for ternary neural network quantization through support and mass equalization","created":"2023-06-30","cited_by_count":0,"area":null},{"id":"2307.08013","title":"Revisiting Implicit Models: Sparsity Trade-offs Capability in Weight-tied Model for Vision Tasks","created":"2023-07-16","cited_by_count":0,"area":null},{"id":"2311.15806","title":"PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2312.07759","title":"IDKM: Memory Efficient Neural Network Quantization via Implicit, Differentiable k-Means","created":"2023-12-12","cited_by_count":0,"area":null},{"id":"2312.08401","title":"Balanced and Deterministic Weight-sharing Helps Network Performance","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2403.19163","title":"D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations","created":"2024-03-28","cited_by_count":0,"area":null},{"id":"2411.00273","title":"Efficient Model Compression for Bayesian Neural Networks","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2501.03095","title":"A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2504.17403","title":"Coding for Computation: Efficient Compression of Neural Networks for Reconfigurable Hardware","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2510.08999","title":"SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2511.14111","title":"CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2601.21219","title":"Soft Quantization: Model Compression Via Weight Coupling","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.08080","title":"The CAPSARII Approach to Cyber-Secure Wearable, Ultra-Low-Power Networked Sensors for Soldier Health Monitoring","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2605.15551","title":"Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2609.31564","title":"Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}