SOTAVerified

Model Compression

Model Compression is an actively pursued area of research over the last few years with the goal of deploying state-of-the-art deep networks in low-power and resource limited devices without significant drop in accuracy. Parameter pruning, low-rank factorization and weight quantization are some of the proposed methods to compress the size of deep networks.

Source: KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 501–550 of 1356 papers

TitleStatusHype
Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation—0
Explaining Sequence-Level Knowledge Distillation as Data-Augmentation for Neural Machine Translation—0
Comprehensive Survey of Model Compression and Speed up for Vision Transformers—0
Exploiting Domain Knowledge via Grouped Weight Sharing with Application to Text Categorization—0
Are We There Yet? A Measurement Study of Efficiency for LLM Applications on Mobile Devices—0
Exploiting Non-Linear Redundancy for Neural Model Compression—0
GeneCAI: Genetic Evolution for Acquiring Compact AI—0
Exploration and Estimation for Model Compression—0
GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference—0
Artemis: HE-Aware Training for Efficient Privacy-Preserving Machine Learning—0
Data-Driven Compression of Convolutional Neural Networks—0
A Unified Knowledge Distillation Framework for Deep Directed Graphical Models—0
DarkRank: Accelerating Deep Metric Learning via Cross Sample Similarities Transfer—0
DARC: Differentiable ARchitecture Compression—0
A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM—0
Aligned Weight Regularizers for Pruning Pretrained Neural Networks—0
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks—0
D^2MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving—0
A Unified Approximation Framework for Compressing and Accelerating Deep Neural Networks—0
CURing Large Models: Compression via CUR Decomposition—0
CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness—0
Augmenting Knowledge Distillation With Peer-To-Peer Mutual Learning For Model Compression—0
Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation—0
CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression—0
Deep Face Recognition Model Compression via Knowledge Transfer and Distillation—0
From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs—0
Cross Domain Model Compression by Structurally Weight Sharing—0
Inferring ECG from PPG for Continuous Cardiac Monitoring Using Lightweight Neural Network—0
From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models—0
Cross-Channel Intragroup Sparsity Neural Network—0
Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systems—0
Attention Sinks and Outlier Features: A 'Catch, Tag, and Release' Mechanism for Embeddings—0
Creating Lightweight Object Detectors with Model Compression for Deployment on Edge Devices—0
CPTQuant -- A Novel Mixed Precision Post-Training Quantization Techniques for Large Language Models—0
ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks—0
AACP: Model Compression by Accurate and Automatic Channel Pruning—0
Frustratingly Easy Model Ensemble for Abstractive Summarization—0
FSCNN: A Fast Sparse Convolution Neural Network Inference System—0
Atrial Fibrillation Detection Using Weight-Pruned, Log-Quantised Convolutional Neural Networks—0
“Learning-Compression” Algorithms for Neural Net Pruning—0
Integrating Fairness and Model Pruning Through Bi-level Optimization—0
CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction—0
Atomic Compression Networks—0
Fragile Mastery: Are Domain-Specific Trade-Offs Undermining On-Device Language Models?—0
Atleus: Accelerating Transformers on the Edge Enabled by 3D Heterogeneous Manycore Architectures—0
Cosine Similarity Knowledge Distillation for Individual Class Information Transfer—0
Spike-and-slab shrinkage priors for structurally sparse Bayesian neural networks—0
CORSD: Class-Oriented Relational Self Distillation—0
A Theoretical Understanding of Neural Network Compression from Sparse Linear Approximation—0
A Half-Space Stochastic Projected Gradient Method for Group Sparsity Regularization—0
Show:102550
← PrevPage 11 of 28Next →
All datasetsImageNetQNLI

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ADLIK-MO-ResNet50+W4A4Top-177.88—Unverified
2ADLIK-MO-ResNet50+W3A4Top-177.34—Unverified
3ResNet-18 + 4bit-1dim model compression using DKMTop-170.52—Unverified
4MobileNet-v1 + 4bit-1dim model compression using DKMTop-169.63—Unverified
5ResNet-18 + 2bit-1dim model compression using DKMTop-168.63—Unverified
6MobileNet-v1 + 2bit-1dim model compression using DKMTop-167.62—Unverified
7ResNet-18 + 4bit-4dim model compression using DKMTop-166.1—Unverified
8ResNet-18 + 2bit-2dim model compression using DKMTop-164.7—Unverified
9MobileNet-v1 + 4bit-4dim model compression using DKMTop-161.4—Unverified
10ResNet-18 + 1bit-1dim model compression using DKMTop-159.7—Unverified
#ModelMetricClaimedVerifiedStatus
1MobileBERT + 2bit-1dim model compression using DKMAccuracy82.13—Unverified
2MobileBERT + 1bit-1dim model compression using DKMAccuracy63.17—Unverified