{"total":166,"rows":[{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864,"area":null},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"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":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"id":"2312.04564","title":"EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS","created":"2023-12-07","cited_by_count":196,"area":null},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183,"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":"2311.18159","title":"CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization","created":"2023-11-30","cited_by_count":130,"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":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"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":"2102.04503","title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","created":"2021-02-08","cited_by_count":64,"area":null},{"id":"2103.05579","title":"hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices","created":"2021-03-09","cited_by_count":62,"area":null},{"id":"2305.15896","title":"MixFormerV2: Efficient Fully Transformer Tracking","created":"2023-05-25","cited_by_count":57,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2411.02530","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","created":"2024-10-30","cited_by_count":36,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"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":"2507.11783","title":"EEG Foundation Models: A Critical Review of Current Progress and Future Directions","created":"2025-07-15","cited_by_count":32,"area":null},{"id":"2102.11289","title":"Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference","created":"2021-02-22","cited_by_count":31,"area":null},{"id":"2110.08152","title":"Kronecker Decomposition for GPT Compression","created":"2021-10-15","cited_by_count":28,"area":null},{"id":"2301.00767","title":"A Survey on Federated Recommendation Systems","created":"2022-12-27","cited_by_count":25,"area":null},{"id":"2207.01580","title":"Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks","created":"2022-07-04","cited_by_count":24,"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":"2301.09858","title":"PowerQuant: Automorphism Search for Non-Uniform Quantization","created":"2023-01-24","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":"2203.08991","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","created":"2022-03-16","cited_by_count":19,"area":null},{"id":"2104.15129","title":"Stealthy Backdoors as Compression Artifacts","created":"2021-04-30","cited_by_count":18,"area":null},{"id":"2106.04563","title":"XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation","created":"2021-06-08","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":"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":"2211.03300","title":"HFedMS: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaverse","created":"2022-11-07","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":"2410.13780","title":"Optimal Quantization for Matrix Multiplication","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2203.10135","title":"Learning Compressed Embeddings for On-Device Inference","created":"2022-03-18","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":"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":"2104.11849","title":"Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics","created":"2021-04-24","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":"2310.06756","title":"Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory","created":"2023-10-10","cited_by_count":12,"area":null},{"id":"2205.14510","title":"Q-LIC: Quantizing Learned Image Compression with Channel Splitting","created":"2022-05-28","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":"2308.05600","title":"NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search","created":"2023-08-10","cited_by_count":8,"area":null},{"id":"2309.15467","title":"Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey","created":"2023-09-27","cited_by_count":8,"area":null},{"id":"2102.02147","title":"Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platforms","created":"2021-02-03","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":"2110.01899","title":"Random matrices in service of ML footprint: ternary random features with no performance loss","created":"2021-10-05","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":"2205.03824","title":"A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges","created":"2022-05-08","cited_by_count":7,"area":null},{"id":"2208.06064","title":"Mixed-Precision Neural Networks: A Survey","created":"2022-08-11","cited_by_count":7,"area":null},{"id":"2311.00447","title":"On the Opportunities of Green Computing: A Survey","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2101.04935","title":"Single-path Bit Sharing for Automatic Loss-aware Model Compression","created":"2021-01-13","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":"2105.01420","title":"Training Quantized Neural Networks to Global Optimality via Semidefinite Programming","created":"2021-05-04","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":"2211.11647","title":"Benchmarking Edge Computing Devices for Grape Bunches and Trunks Detection using Accelerated Object Detection Single Shot MultiBox Deep Learning Models","created":"2022-11-21","cited_by_count":6,"area":null},{"id":"2303.02668","title":"Knowledge-Enhanced Semi-Supervised Federated Learning for Aggregating Heterogeneous Lightweight Clients in IoT","created":"2023-03-05","cited_by_count":6,"area":null},{"id":"2103.14224","title":"Active multi-fidelity Bayesian online changepoint detection","created":"2021-03-26","cited_by_count":5,"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":"2111.10854","title":"XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks","created":"2021-11-21","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":"2307.03936","title":"Towards Efficient In-memory Computing Hardware for Quantized Neural Networks: State-of-the-art, Open Challenges and Perspectives","created":"2023-07-08","cited_by_count":5,"area":null},{"id":"2505.03031","title":"Radio: Rate-Distortion Optimization for Large Language Model Compression","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2111.09348","title":"End-to-End Learned Image Compression with Quantized Weights and Activations","created":"2021-11-17","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":"2203.03794","title":"YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers","created":"2022-03-08","cited_by_count":4,"area":null},{"id":"2207.12773","title":"Quiver neural networks","created":"2022-07-26","cited_by_count":4,"area":null},{"id":"2212.01957","title":"CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness","created":"2022-12-04","cited_by_count":4,"area":null},{"id":"2212.05326","title":"Vertical Layering of Quantized Neural Networks for Heterogeneous Inference","created":"2022-12-10","cited_by_count":4,"area":null},{"id":"2212.12653","title":"Hyperspherical Quantization: Toward Smaller and More Accurate Models","created":"2022-12-24","cited_by_count":4,"area":null},{"id":"2306.02433","title":"Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation","created":"2023-06-04","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":"2105.01064","title":"Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems","created":"2021-05-04","cited_by_count":3,"area":null},{"id":"2202.12943","title":"Arrhythmia Classifier Using Convolutional Neural Network with Adaptive Loss-aware Multi-bit Networks Quantization","created":"2022-02-27","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":"2210.08065","title":"Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic Locomotion","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2302.06405","title":"An Optical XNOR-Bitcount Based Accelerator for Efficient Inference of Binary Neural Networks","created":"2023-02-03","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":"2402.19264","title":"T3DNet: Compressing Point Cloud Models for Lightweight 3D Recognition","created":"2024-02-29","cited_by_count":3,"area":null},{"id":"2405.14222","title":"Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models","created":"2024-05-23","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":"2104.02306","title":"Binary Neural Network for Speaker Verification","created":"2021-04-06","cited_by_count":2,"area":null},{"id":"2104.11295","title":"On Geodesic Distances and Contextual Embedding Compression for Text Classification","created":"2021-04-22","cited_by_count":2,"area":null},{"id":"2107.06960","title":"MAFAT: Memory-Aware Fusing and Tiling of Neural Networks for Accelerated Edge Inference","created":"2021-07-14","cited_by_count":2,"area":null},{"id":"2110.14794","title":"Masked LARk: Masked Learning, Aggregation and Reporting worKflow","created":"2021-10-27","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":"2203.15980","title":"DELTA: Dynamically Optimizing GPU Memory beyond Tensor Recomputation","created":"2022-03-30","cited_by_count":2,"area":null},{"id":"2211.11397","title":"Learning Low-Rank Representations for Model Compression","created":"2022-11-21","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":"2306.16869","title":"NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes","created":"2023-06-29","cited_by_count":2,"area":null},{"id":"2402.03142","title":"Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models","created":"2024-02-05","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":"2409.02026","title":"Foundations of Large Language Model Compression -- Part 1: Weight Quantization","created":"2024-09-03","cited_by_count":2,"area":null}],"next_cursor":"100"}