{"total":149,"rows":[{"id":"2311.17245","title":"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS","created":"2023-11-28","cited_by_count":436,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2104.08378","title":"Accelerating Sparse Deep Neural Networks","created":"2021-04-16","cited_by_count":223,"area":null},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154,"area":null},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115,"area":null},{"id":"2312.11983","title":"Fluctuation-based Adaptive Structured Pruning for Large Language Models","created":"2023-12-19","cited_by_count":111,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66,"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":"2212.09095","title":"Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale","created":"2022-12-18","cited_by_count":64,"area":"lr"},{"id":"2403.02991","title":"MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer","created":"2024-03-05","cited_by_count":54,"area":"inference"},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50,"area":null},{"id":"2412.18110","title":"SlimGPT: Layer-wise Structured Pruning for Large Language Models","created":"2024-12-24","cited_by_count":44,"area":null},{"id":"2402.05406","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","created":"2024-02-08","cited_by_count":43,"area":null},{"id":"2305.08746","title":"Seeing is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability","created":"2023-05-04","cited_by_count":38,"area":"mechinterp"},{"id":"2102.03214","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","created":"2021-02-05","cited_by_count":30,"area":null},{"id":"2207.06646","title":"DropNet: Reducing Neural Network Complexity via Iterative Pruning","created":"2022-07-14","cited_by_count":29,"area":null},{"id":"2309.11932","title":"A Machine Learning-oriented Survey on Tiny Machine Learning","created":"2023-09-21","cited_by_count":27,"area":null},{"id":"2308.07209","title":"Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning","created":"2023-08-14","cited_by_count":23,"area":null},{"id":"2105.13331","title":"Quantization and Deployment of Deep Neural Networks on Microcontrollers","created":"2021-05-27","cited_by_count":21,"area":null},{"id":"2105.01015","title":"Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization","created":"2021-05-03","cited_by_count":19,"area":null},{"id":"2108.12594","title":"Layer-wise Model Pruning based on Mutual Information","created":"2021-08-28","cited_by_count":19,"area":null},{"id":"2505.22689","title":"SlimLLM: Accurate Structured Pruning for Large Language Models","created":"2025-05-28","cited_by_count":18,"area":null},{"id":"2109.09829","title":"Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework","created":"2021-09-20","cited_by_count":17,"area":null},{"id":"2306.14306","title":"Adaptive Sharpness-Aware Pruning for Robust Sparse Networks","created":"2023-06-25","cited_by_count":17,"area":null},{"id":"2110.08350","title":"Differentiable Network Pruning for Microcontrollers","created":"2021-10-15","cited_by_count":16,"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":"2211.05910","title":"Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report","created":"2022-11-07","cited_by_count":16,"area":null},{"id":"2310.03652","title":"Extreme sparsification of physics-augmented neural networks for interpretable model discovery in mechanics","created":"2023-10-05","cited_by_count":16,"area":null},{"id":"2312.12791","title":"Model-Based Control with Sparse Neural Dynamics","created":"2023-12-20","cited_by_count":16,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2210.02506","title":"Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors","created":"2022-10-05","cited_by_count":14,"area":null},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2211.06088","title":"RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization","created":"2022-11-11","cited_by_count":13,"area":null},{"id":"2109.14960","title":"Prune Your Model Before Distill It","created":"2021-09-30","cited_by_count":12,"area":"distill"},{"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":"2305.11203","title":"PDP: Parameter-free Differentiable Pruning is All You Need","created":"2023-05-18","cited_by_count":12,"area":null},{"id":"2311.15578","title":"Experimental Analysis of Large-scale Learnable Vector Storage Compression","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2310.20682","title":"Compression with Exact Error Distribution for Federated Learning","created":"2023-10-31","cited_by_count":11,"area":null},{"id":"2301.05345","title":"GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer","created":"2023-01-13","cited_by_count":10,"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":"2501.15316","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","created":"2025-01-25","cited_by_count":10,"area":"moe"},{"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":"2211.13771","title":"Towards Practical Control of Singular Values of Convolutional Layers","created":"2022-11-24","cited_by_count":9,"area":null},{"id":"2307.10981","title":"PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attacks","created":"2023-07-20","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":"2312.05795","title":"Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup","created":"2023-12-10","cited_by_count":8,"area":"mllm"},{"id":"2407.19126","title":"Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining","created":"2024-07-26","cited_by_count":8,"area":null},{"id":"2203.03445","title":"S-Rocket: Selective Random Convolution Kernels for Time Series Classification","created":"2022-03-07","cited_by_count":7,"area":null},{"id":"2205.10369","title":"Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compression","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2508.10227","title":"EntropyGS: An Efficient Entropy Coding on 3D Gaussian Splatting","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2307.05352","title":"Leveraging Variational Autoencoders for Parameterized MMSE Estimation","created":"2023-07-11","cited_by_count":6,"area":null},{"id":"2405.20314","title":"S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs","created":"2024-05-30","cited_by_count":6,"area":"inference"},{"id":"2101.12016","title":"Baseline Pruning-Based Approach to Trojan Detection in Neural Networks","created":"2021-01-22","cited_by_count":5,"area":null},{"id":"2103.03483","title":"Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices","created":"2021-03-05","cited_by_count":5,"area":null},{"id":"2209.13590","title":"Sauron U-Net: Simple automated redundancy elimination in medical image segmentation via filter pruning","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2210.00313","title":"CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family","created":"2022-10-01","cited_by_count":5,"area":null},{"id":"2306.15337","title":"Homological Neural Networks: A Sparse Architecture for Multivariate Complexity","created":"2023-06-27","cited_by_count":5,"area":null},{"id":"2403.14047","title":"Accelerating ViT Inference on FPGA through Static and Dynamic Pruning","created":"2024-03-21","cited_by_count":5,"area":"inference"},{"id":"2411.06448","title":"Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation","created":"2024-11-10","cited_by_count":5,"area":"distill"},{"id":"2507.12988","title":"Variance-Based Pruning for Accelerating and Compressing Trained Networks","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2101.05363","title":"NetCut: Real-Time DNN Inference Using Layer Removal","created":"2021-01-13","cited_by_count":4,"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":"2108.09081","title":"FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update","created":"2021-08-20","cited_by_count":4,"area":null},{"id":"2111.08577","title":"Neuron-based Pruning of Deep Neural Networks with Better Generalization using Kronecker Factored Curvature Approximation","created":"2021-11-16","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":"2208.00331","title":"CoNLoCNN: Exploiting Correlation and Non-Uniform Quantization for Energy-Efficient Low-precision Deep Convolutional Neural Networks","created":"2022-07-31","cited_by_count":4,"area":null},{"id":"2210.08578","title":"Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices","created":"2022-10-16","cited_by_count":4,"area":null},{"id":"2307.08771","title":"UPSCALE: Unconstrained Channel Pruning","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2309.14162","title":"Data Upcycling Knowledge Distillation for Image Super-Resolution","created":"2023-09-25","cited_by_count":4,"area":"distill"},{"id":"2309.17211","title":"Data-Free Dynamic Compression of CNNs for Tractable Efficiency","created":"2023-09-29","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":"2510.17700","title":"Elastic ViTs from Pretrained Models without Retraining","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2605.14075","title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2103.07674","title":"Efficient Sparse Artificial Neural Networks","created":"2021-03-13","cited_by_count":3,"area":null},{"id":"2107.04191","title":"Structured Model Pruning of Convolutional Networks on Tensor Processing Units","created":"2021-07-09","cited_by_count":3,"area":null},{"id":"2108.06128","title":"Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices","created":"2021-08-13","cited_by_count":3,"area":null},{"id":"2109.15014","title":"Deep Neural Compression Via Concurrent Pruning and Self-Distillation","created":"2021-09-30","cited_by_count":3,"area":"distill"},{"id":"2205.01235","title":"Triangular Dropout: Variable Network Width without Retraining","created":"2022-05-02","cited_by_count":3,"area":null},{"id":"2303.16214","title":"Tetra-AML: Automatic Machine Learning via Tensor Networks","created":"2023-03-28","cited_by_count":3,"area":null},{"id":"2303.16999","title":"PopSparse: Accelerated block sparse matrix multiplication on IPU","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2309.01771","title":"ADC/DAC-Free Analog Acceleration of Deep Neural Networks with Frequency Transformation","created":"2023-09-04","cited_by_count":3,"area":null},{"id":"2311.09858","title":"Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets","created":"2023-11-16","cited_by_count":3,"area":null},{"id":"2402.05146","title":"Compressing Deep Reinforcement Learning Networks with a Dynamic Structured Pruning Method for Autonomous Driving","created":"2024-02-07","cited_by_count":3,"area":"driving"},{"id":"2502.17941","title":"Optimal Brain Apoptosis","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2507.16872","title":"CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2103.00793","title":"Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network","created":"2021-03-01","cited_by_count":2,"area":"distill"},{"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":"2109.02909","title":"BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables","created":"2021-09-07","cited_by_count":2,"area":null},{"id":"2111.05950","title":"Self-Compression in Bayesian Neural Networks","created":"2021-11-10","cited_by_count":2,"area":null},{"id":"2112.08227","title":"An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2202.04303","title":"TinyM$^2$Net: A Flexible System Algorithm Co-designed Multimodal Learning Framework for Tiny Devices","created":"2022-02-09","cited_by_count":2,"area":null},{"id":"2204.03479","title":"Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention","created":"2022-03-20","cited_by_count":2,"area":null},{"id":"2212.08815","title":"FSCNN: A Fast Sparse Convolution Neural Network Inference System","created":"2022-12-17","cited_by_count":2,"area":null},{"id":"2301.04502","title":"Pruning Compact ConvNets for Efficient Inference","created":"2023-01-11","cited_by_count":2,"area":null},{"id":"2307.11904","title":"Model Compression Methods for YOLOv5: A Review","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2407.15875","title":"Shapley Pruning for Neural Network Compression","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2501.16917","title":"B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM Pruning","created":"2025-01-28","cited_by_count":2,"area":null},{"id":"2503.21928","title":"An Efficient Training Algorithm for Models with Block-wise Sparsity","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2107.03909","title":"Weight Reparametrization for Budget-Aware Network Pruning","created":"2021-07-08","cited_by_count":1,"area":null}],"next_cursor":"100"}