{"total":263,"rows":[{"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":"2311.03099","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","created":"2023-11-06","cited_by_count":694,"area":null},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322,"area":null},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131,"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":"2312.17238","title":"Fast Inference of Mixture-of-Experts Language Models with Offloading","created":"2023-12-28","cited_by_count":91,"area":"moe"},{"id":"2304.01195","title":"Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement","created":"2023-04-03","cited_by_count":84,"area":null},{"id":"2201.12904","title":"COIN++: Neural Compression Across Modalities","created":"2022-01-30","cited_by_count":82,"area":null},{"id":"2212.07048","title":"PD-Quant: Post-Training Quantization based on Prediction Difference Metric","created":"2022-12-14","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":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2402.03666","title":"QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning","created":"2024-02-06","cited_by_count":49,"area":"diffusion"},{"id":"2303.02552","title":"An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry","created":"2023-03-05","cited_by_count":47,"area":null},{"id":"2301.06574","title":"Causal Recurrent Variational Autoencoder for Medical Time Series Generation","created":"2023-01-16","cited_by_count":45,"area":null},{"id":"2203.08737","title":"Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey","created":"2022-03-16","cited_by_count":39,"area":null},{"id":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2202.05239","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2112.10769","title":"Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats","created":"2021-12-19","cited_by_count":26,"area":null},{"id":"2309.14021","title":"LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression","created":"2023-09-25","cited_by_count":26,"area":null},{"id":"2210.05866","title":"Deep Learning for Iris Recognition: A Survey","created":"2022-10-12","cited_by_count":25,"area":null},{"id":"2312.00333","title":"Green Edge AI: A Contemporary Survey","created":"2023-12-01","cited_by_count":25,"area":null},{"id":"2411.13918","title":"Quantization without Tears","created":"2024-11-21","cited_by_count":25,"area":null},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24,"area":null},{"id":"2406.02500","title":"Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques","created":"2024-06-04","cited_by_count":24,"area":"moe"},{"id":"2503.02891","title":"Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies","created":"2025-02-26","cited_by_count":24,"area":null},{"id":"2303.13363","title":"FS-Real: Towards Real-World Cross-Device Federated Learning","created":"2023-03-23","cited_by_count":22,"area":null},{"id":"2404.01365","title":"Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation","created":"2024-04-01","cited_by_count":21,"area":"moe"},{"id":"2412.11041","title":"Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models","created":"2024-12-15","cited_by_count":20,"area":"alignment"},{"id":"2205.11269","title":"Dynamic Split Computing for Efficient Deep Edge Intelligence","created":"2022-05-23","cited_by_count":18,"area":null},{"id":"2311.13171","title":"ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization","created":"2023-11-22","cited_by_count":18,"area":null},{"id":"2209.10986","title":"Learning to Simulate Realistic LiDARs","created":"2022-09-22","cited_by_count":16,"area":null},{"id":"2311.01057","title":"Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO","created":"2023-11-02","cited_by_count":15,"area":null},{"id":"2509.09090","title":"SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models","created":"2025-09-11","cited_by_count":15,"area":"vla"},{"id":"2201.07706","title":"Object Detection in Autonomous Vehicles: Status and Open Challenges","created":"2022-01-19","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":"2201.01709","title":"The Effect of Model Compression on Fairness in Facial Expression Recognition","created":"2022-01-05","cited_by_count":13,"area":null},{"id":"2206.01838","title":"Differentially Private Model Compression","created":"2022-06-03","cited_by_count":13,"area":null},{"id":"2407.00118","title":"From Efficient Multimodal Models to World Models: A Survey","created":"2024-06-27","cited_by_count":13,"area":"wm"},{"id":"2211.10155","title":"Structured Pruning Adapters","created":"2022-11-17","cited_by_count":12,"area":null},{"id":"2309.02065","title":"Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI","created":"2023-09-05","cited_by_count":12,"area":null},{"id":"2312.08893","title":"Solving Dense Linear Systems Faster Than via Preconditioning","created":"2023-12-14","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":"2301.12378","title":"Towards Inference Efficient Deep Ensemble Learning","created":"2023-01-29","cited_by_count":11,"area":null},{"id":"2307.05999","title":"Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems","created":"2023-07-12","cited_by_count":11,"area":null},{"id":"2403.01929","title":"Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet?","created":"2024-03-04","cited_by_count":11,"area":null},{"id":"2505.18713","title":"Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer","created":"2025-05-24","cited_by_count":11,"area":null},{"id":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2205.10828","title":"What Do Compressed Multilingual Machine Translation Models Forget?","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2207.10188","title":"Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach","created":"2022-07-20","cited_by_count":9,"area":null},{"id":"2207.13050","title":"Efficient High-Resolution Deep Learning: A Survey","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2307.07705","title":"CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal Devices","created":"2023-07-15","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":"2505.02309","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","created":"2025-05-05","cited_by_count":9,"area":null},{"id":"2110.10305","title":"When in Doubt, Summon the Titans: Efficient Inference with Large Models","created":"2021-10-19","cited_by_count":8,"area":null},{"id":"2206.11233","title":"Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review","created":"2022-06-20","cited_by_count":8,"area":null},{"id":"2304.02595","title":"Bayesian neural networks via MCMC: a Python-based tutorial","created":"2023-04-02","cited_by_count":8,"area":null},{"id":"2307.12659","title":"A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization","created":"2023-07-24","cited_by_count":8,"area":null},{"id":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2503.01874","title":"CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging","created":"2025-02-26","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":"2110.08271","title":"Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations","created":"2021-10-15","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":"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":"2205.08358","title":"Perturbation of Deep Autoencoder Weights for Model Compression and Classification of Tabular Data","created":"2022-05-17","cited_by_count":7,"area":null},{"id":"2208.12866","title":"Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2210.01625","title":"Energy Consumption of Neural Networks on NVIDIA Edge Boards: an Empirical Model","created":"2022-10-04","cited_by_count":7,"area":null},{"id":"2304.09876","title":"Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing","created":"2023-04-19","cited_by_count":7,"area":null},{"id":"2308.04168","title":"EFaR 2023: Efficient Face Recognition Competition","created":"2023-08-08","cited_by_count":7,"area":null},{"id":"2402.15978","title":"Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood","created":"2024-02-25","cited_by_count":7,"area":null},{"id":"2408.01055","title":"Towards Agentic Runtime Healing","created":"2024-08-02","cited_by_count":7,"area":"agents"},{"id":"2502.12923","title":"On-Device LLMs for Home Assistant: Dual Role in Intent Detection and Response Generation","created":"2025-02-18","cited_by_count":7,"area":null},{"id":"2507.18725","title":"The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models","created":"2025-07-24","cited_by_count":7,"area":"safety"},{"id":"2507.19360","title":"EA-ViT: Efficient Adaptation for Elastic Vision Transformer","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2205.11913","title":"Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy, Challenges and Vision","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2407.04803","title":"The Impact of Quantization and Pruning on Deep Reinforcement Learning Models","created":"2024-07-05","cited_by_count":6,"area":"deeprl"},{"id":"2410.03843","title":"TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2505.21591","title":"Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning","created":"2025-05-27","cited_by_count":6,"area":"diffusion"},{"id":"2206.05916","title":"Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks","created":"2022-06-13","cited_by_count":5,"area":null},{"id":"2301.00652","title":"Efficient Speech Representation Learning with Low-Bit Quantization","created":"2022-12-14","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":"2310.12612","title":"How a student becomes a teacher: learning and forgetting through Spectral methods","created":"2023-10-19","cited_by_count":5,"area":"distill"},{"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":"2410.19274","title":"Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking","created":"2024-10-25","cited_by_count":5,"area":null},{"id":"2412.03587","title":"Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models","created":"2024-11-26","cited_by_count":5,"area":null},{"id":"2501.05515","title":"Neural Architecture Codesign for Fast Physics Applications","created":"2025-01-09","cited_by_count":5,"area":null},{"id":"2505.20932","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2506.18927","title":"From Tiny Machine Learning to Tiny Deep Learning: A Survey","created":"2025-06-21","cited_by_count":5,"area":null},{"id":"2108.00259","title":"How much pre-training is enough to discover a good subnetwork?","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2109.05075","title":"On the Compression of Neural Networks Using $\\ell_0$-Norm Regularization and Weight Pruning","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2204.01460","title":"Optimizing the Consumption of Spiking Neural Networks with Activity Regularization","created":"2022-04-04","cited_by_count":4,"area":null},{"id":"2204.03326","title":"Enabling All In-Edge Deep Learning: A Literature Review","created":"2022-04-07","cited_by_count":4,"area":null},{"id":"2204.11444","title":"Boosting Pruned Networks with Linear Over-parameterization","created":"2022-04-25","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":"2305.18665","title":"E-PANNs: Sound Recognition Using Efficient Pre-trained Audio Neural Networks","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2307.08657","title":"Neural Image Compression: Generalization, Robustness, and Spectral Biases","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2309.06047","title":"Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing","created":"2023-09-12","cited_by_count":4,"area":null},{"id":"2401.14110","title":"Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators","created":"2024-01-25","cited_by_count":4,"area":null},{"id":"2405.05865","title":"Faster Linear Systems and Matrix Norm Approximation via Multi-level Sketched Preconditioning","created":"2024-05-09","cited_by_count":4,"area":null}],"next_cursor":"100"}