{"total":150,"rows":[{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2312.04564","title":"EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS","created":"2023-12-07","cited_by_count":196,"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":"2104.02151","title":"Distributed Learning in Wireless Networks: Recent Progress and Future Challenges","created":"2021-04-05","cited_by_count":129,"area":null},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98,"area":null},{"id":"2309.06497","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","created":"2023-09-12","cited_by_count":77,"area":null},{"id":"2104.03438","title":"Convolutional Neural Network Pruning with Structural Redundancy Reduction","created":"2021-04-08","cited_by_count":73,"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":"2103.10559","title":"CDFI: Compression-Driven Network Design for Frame Interpolation","created":"2021-03-18","cited_by_count":56,"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":"2106.10860","title":"Multiplying Matrices Without Multiplying","created":"2021-06-21","cited_by_count":30,"area":null},{"id":"2310.02556","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","created":"2023-10-04","cited_by_count":29,"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":"2301.09858","title":"PowerQuant: Automorphism Search for Non-Uniform Quantization","created":"2023-01-24","cited_by_count":20,"area":null},{"id":"2404.06091","title":"Hash3D: Training-free Acceleration for 3D Generation","created":"2024-04-09","cited_by_count":19,"area":"diffusion"},{"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":"2104.07085","title":"Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks","created":"2021-04-14","cited_by_count":14,"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":"2206.04662","title":"DiSparse: Disentangled Sparsification for Multitask Model Compression","created":"2022-06-09","cited_by_count":14,"area":null},{"id":"2305.12102","title":"Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems","created":"2023-05-20","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":"2406.15575","title":"Sketch-GNN: Scalable Graph Neural Networks with Sublinear Training Complexity","created":"2024-06-21","cited_by_count":14,"area":null},{"id":"2201.02711","title":"Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks","created":"2022-01-07","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":"2204.05436","title":"Heterogeneous Acceleration Pipeline for Recommendation System Training","created":"2022-04-11","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":"2302.03505","title":"OPORP: One Permutation + One Random Projection","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2209.02869","title":"Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps","created":"2022-09-07","cited_by_count":11,"area":null},{"id":"2301.12860","title":"Massively Scaling Heteroscedastic Classifiers","created":"2023-01-30","cited_by_count":11,"area":null},{"id":"2302.04464","title":"Towards Fairer and More Efficient Federated Learning via Multidimensional Personalized Edge Models","created":"2023-02-09","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":"2106.00050","title":"Continual 3D Convolutional Neural Networks for Real-time Processing of Videos","created":"2021-05-31","cited_by_count":9,"area":null},{"id":"2303.03382","title":"Globally Optimal Training of Neural Networks with Threshold Activation Functions","created":"2023-03-06","cited_by_count":9,"area":null},{"id":"2307.00498","title":"Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning","created":"2023-07-02","cited_by_count":9,"area":null},{"id":"2403.19490","title":"Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment","created":"2024-03-28","cited_by_count":9,"area":null},{"id":"2208.05969","title":"Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment","created":"2022-08-11","cited_by_count":8,"area":null},{"id":"2210.11698","title":"Learning Robust Dynamics through Variational Sparse Gating","created":"2022-10-21","cited_by_count":8,"area":"wm"},{"id":"2308.05600","title":"NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search","created":"2023-08-10","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":"2103.06124","title":"Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems","created":"2021-02-24","cited_by_count":7,"area":null},{"id":"2204.02965","title":"LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2107.12673","title":"COPS: Controlled Pruning Before Training Starts","created":"2021-07-27","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":"2203.14645","title":"REx: Data-Free Residual Quantization Error Expansion","created":"2022-03-28","cited_by_count":6,"area":null},{"id":"2208.04461","title":"A Theoretical View on Sparsely Activated Networks","created":"2022-08-08","cited_by_count":6,"area":"moe"},{"id":"2209.04551","title":"Sparsity-guided Network Design for Frame Interpolation","created":"2022-09-09","cited_by_count":6,"area":null},{"id":"2107.06916","title":"Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion","created":"2021-07-14","cited_by_count":5,"area":null},{"id":"2107.07110","title":"Compact and Optimal Deep Learning with Recurrent Parameter Generators","created":"2021-07-15","cited_by_count":5,"area":null},{"id":"2202.13736","title":"On the Robustness of CountSketch to Adaptive Inputs","created":"2022-02-28","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":"2305.01868","title":"Pre-train and Search: Efficient Embedding Table Sharding with Pre-trained Neural Cost Models","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2306.01751","title":"Differential Privacy with Random Projections and Sign Random Projections","created":"2023-05-22","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":"2310.11611","title":"In defense of parameter sharing for model-compression","created":"2023-10-17","cited_by_count":5,"area":null},{"id":"2504.02168","title":"MDP: Multidimensional Vision Model Pruning with Latency Constraint","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2108.02191","title":"Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\\times$ Compression and 3.1$\\times$ Faster Inference","created":"2021-08-04","cited_by_count":4,"area":null},{"id":"2109.03513","title":"Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks","created":"2021-09-08","cited_by_count":4,"area":null},{"id":"2110.09508","title":"Deep CNNs for Peripheral Blood Cell Classification","created":"2021-10-18","cited_by_count":4,"area":null},{"id":"2202.07221","title":"Navigating Local Minima in Quantized Spiking Neural Networks","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2302.08571","title":"A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2406.12079","title":"Multi-Dimensional Pruning: Joint Channel, Layer and Block Pruning with Latency Constraint","created":"2024-06-17","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":"2408.05247","title":"Early-Exit meets Model-Distributed Inference at Edge Networks","created":"2024-08-08","cited_by_count":4,"area":"inference"},{"id":"2509.17968","title":"Visual Detector Compression via Location-Aware Discriminant Analysis","created":"2025-09-22","cited_by_count":4,"area":null},{"id":"2110.12478","title":"Deep Asymmetric Hashing with Dual Semantic Regression and Class Structure Quantization","created":"2021-10-24","cited_by_count":3,"area":null},{"id":"2209.03450","title":"Seeking Interpretability and Explainability in Binary Activated Neural Networks","created":"2022-09-07","cited_by_count":3,"area":null},{"id":"2209.09868","title":"Streaming Encoding Algorithms for Scalable Hyperdimensional Computing","created":"2022-09-20","cited_by_count":3,"area":null},{"id":"2305.07205","title":"Mem-Rec: Memory Efficient Recommendation System using Alternative Representation","created":"2023-05-12","cited_by_count":3,"area":null},{"id":"2307.11862","title":"Digital Modeling on Large Kernel Metamaterial Neural Network","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2409.03945","title":"TropNNC: Structured Neural Network Compression Using Tropical Geometry","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2410.06364","title":"Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2101.08696","title":"Sum-Rate-Distortion Function for Indirect Multiterminal Source Coding in Federated Learning","created":"2021-01-21","cited_by_count":2,"area":null},{"id":"2102.01341","title":"Benchmarking Quantized Neural Networks on FPGAs with FINN","created":"2021-02-02","cited_by_count":2,"area":null},{"id":"2102.02193","title":"CountSketches, Feature Hashing and the Median of Three","created":"2021-02-03","cited_by_count":2,"area":null},{"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":"2111.14836","title":"Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers","created":"2021-11-29","cited_by_count":2,"area":null},{"id":"2207.00956","title":"Tricking the Hashing Trick: A Tight Lower Bound on the Robustness of CountSketch to Adaptive Inputs","created":"2022-07-03","cited_by_count":2,"area":null},{"id":"2207.10702","title":"Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2207.10731","title":"The trade-offs of model size in large recommendation models : A 10000 $\\times$ compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2302.00123","title":"Design and Implementation of A Soccer Ball Detection System with Multiple Cameras","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2303.02512","title":"Visual Saliency-Guided Channel Pruning for Deep Visual Detectors in Autonomous Driving","created":"2023-03-04","cited_by_count":2,"area":null},{"id":"2303.08970","title":"Gated Compression Layers for Efficient Always-On Models","created":"2023-03-15","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":"2405.17568","title":"ExtremeMETA: High-speed Lightweight Image Segmentation Model by Remodeling Multi-channel Metamaterial Imagers","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2412.12371","title":"Priority-Aware Model-Distributed Inference at Edge Networks","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2501.02508","title":"PTEENet: Post-Trained Early-Exit Neural Networks Augmentation for Inference Cost Optimization","created":"2025-01-05","cited_by_count":2,"area":"inference"},{"id":"2510.22767","title":"TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2603.07615","title":"Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2604.07385","title":"Playing DOOM with 1.3M Parameters: Specialized Small Models vs Large Language Models for Real-Time Game Control","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2107.01354","title":"Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks","created":"2021-07-03","cited_by_count":1,"area":null},{"id":"2107.03375","title":"Differentiable Architecture Pruning for Transfer Learning","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2110.10876","title":"Evolving Transferable Neural Pruning Functions","created":"2021-10-21","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":"2307.07816","title":"Minimal Random Code Learning with Mean-KL Parameterization","created":"2023-07-15","cited_by_count":1,"area":null},{"id":"2309.17361","title":"Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2311.10207","title":"Stella Nera: A Differentiable Maddness-Based Hardware Accelerator for Efficient Approximate Matrix Multiplication","created":"2023-11-16","cited_by_count":1,"area":null},{"id":"2401.17098","title":"Deep Learning-Driven Approach for Handwritten Chinese Character Classification","created":"2024-01-30","cited_by_count":1,"area":null}],"next_cursor":"100"}