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 151–200 of 1356 papers

TitleStatusHype
Activation Sparsity Opportunities for Compressing General Large Language Models—0
Can Students Beyond The Teacher? Distilling Knowledge from Teacher's Bias—0
Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices—0
Low-Rank Correction for Quantized LLMs—0
VQ4ALL: Efficient Neural Network Representation via a Universal Codebook—0
Compression for Better: A General and Stable Lossless Compression Framework—0
Lossless Model Compression via Joint Low-Rank Factorization Optimization—0
Trimming Down Large Spiking Vision Transformers via Heterogeneous Quantization Search—0
CPTQuant -- A Novel Mixed Precision Post-Training Quantization Techniques for Large Language Models—0
Efficient Model Compression Techniques with FishLeg—0
Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models—0
Faithful Label-free Knowledge DistillationCode0
Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion—0
TaQ-DiT: Time-aware Quantization for Diffusion Transformers—0
FASTNav: Fine-tuned Adaptive Small-language-models Trained for Multi-point Robot Navigation—0
What Makes a Good Dataset for Knowledge Distillation?—0
Puppet-CNN: Input-Adaptive Convolutional Neural Networks with Model Compression using Ordinary Differential Equation—0
Bridging the Resource Gap: Deploying Advanced Imitation Learning Models onto Affordable Embedded Platforms—0
An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2Code0
Re-Parameterization of Lightweight Transformer for On-Device Speech Emotion Recognition—0
Feature Interaction Fusion Self-Distillation Network For CTR Prediction—0
OWLed: Outlier-weighed Layerwise Pruning for Efficient Autonomous Driving FrameworkCode0
ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization—0
Optimizing Traffic Signal Control using High-Dimensional State Representation and Efficient Deep Reinforcement Learning—0
ZipNN: Lossless Compression for AI ModelsCode3
From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models—0
Change Is the Only Constant: Dynamic LLM Slicing based on Layer RedundancyCode0
Efficient Model Compression for Bayesian Neural Networks—0
ML Research BenchmarkCode0
LLMCBench: Benchmarking Large Language Model Compression for Efficient DeploymentCode1
EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation—0
A Survey of Small Language Models—0
SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models—0
Beware of Calibration Data for Pruning Large Language Models—0
Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion AugmentationCode0
Self-calibration for Language Model Quantization and Pruning—0
Identifying Sub-networks in Neural Networks via Functionally Similar Representations—0
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary SearchCode1
Preview-based Category Contrastive Learning for Knowledge Distillation—0
QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN ModelsCode0
SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight CompressionCode1
What is Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias—0
CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression—0
Large Language Model Compression with Neural Architecture Search—0
QT-DoG: Quantization-aware Training for Domain GeneralizationCode1
SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching—0
ESPACE: Dimensionality Reduction of Activations for Model Compression—0
Continuous Approximations for Improving Quantization Aware Training of LLMs—0
Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models—0
Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model CompressionCode1
Show:102550
← PrevPage 4 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