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 301–350 of 1356 papers

TitleStatusHype
Efficiency optimization of large-scale language models based on deep learning in natural language processing tasks—0
Densely Distilling Cumulative Knowledge for Continual Learning—0
AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting—0
Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models—0
From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks—0
NurtureNet: A Multi-task Video-based Approach for Newborn Anthropometry—0
Light Field Compression Based on Implicit Neural Representation—0
Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision TransformerCode0
Communication-Efficient Federated Learning with Adaptive Compression under Dynamic Bandwidth—0
Iterative Filter Pruning for Concatenation-based CNN ArchitecturesCode0
Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models—0
Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator DesignCode2
FedGreen: Carbon-aware Federated Learning with Model Size Adaptation—0
Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization—0
Data-free Knowledge Distillation for Fine-grained Visual CategorizationCode0
Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads—0
Comprehensive Survey of Model Compression and Speed up for Vision Transformers—0
Structured Model Pruning for Efficient Inference in Computational Pathology—0
Transferable and Principled Efficiency for Open-Vocabulary SegmentationCode1
Simplifying Two-Stage Detectors for On-Device Inference in Remote Sensing—0
Bayesian Federated Model Compression for Communication and Computation Efficiency—0
Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language BehindCode0
Improve Knowledge Distillation via Label Revision and Data Selection—0
Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution—0
On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL—0
Automated Inference of Graph Transformation Rules—0
Enhancing Inference Efficiency of Large Language Models: Investigating Optimization Strategies and Architectural Innovations—0
Instance-Aware Group Quantization for Vision Transformers—0
Streamlining Redundant Layers to Compress Large Language ModelsCode1
Is Modularity Transferable? A Case Study through the Lens of Knowledge DistillationCode0
Dense Vision Transformer Compression with Few Samples—0
Are Compressed Language Models Less Subgroup Robust?Code0
Tiny Models are the Computational Saver for Large ModelsCode0
Order of Compression: A Systematic and Optimal Sequence to Combinationally Compress CNN—0
Magic for the Age of Quantized DNNs—0
Advancing IIoT with Over-the-Air Federated Learning: The Role of Iterative Magnitude Pruning—0
DiPaCo: Distributed Path Composition—0
BRIEDGE: EEG-Adaptive Edge AI for Multi-Brain to Multi-Robot Interaction—0
PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task AdaptationCode1
Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and EfficiencyCode0
SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model CompressionCode3
Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons—0
Enhanced Sparsification via Stimulative Training—0
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic HashingCode1
Optimal Policy Sparsification and Low Rank Decomposition for Deep Reinforcement Learning—0
Towards efficient deep autoencoders for multivariate time series anomaly detection—0
DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time ScalingCode0
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel ApproachCode1
Differentially Private Knowledge Distillation via Synthetic Text GenerationCode0
PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-TuningCode2
Show:102550
← PrevPage 7 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