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 226–250 of 1356 papers

TitleStatusHype
Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks—0
Small Language Models: Architectures, Techniques, Evaluation, Problems and Future Adaptation—0
Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs—0
Efficient Speech Translation through Model Compression and Knowledge DistillationCode0
Knowledge Grafting of Large Language ModelsCode0
Making deep neural networks work for medical audio: representation, compression and domain adaptation—0
Efficient and Workload-Aware LLM Serving via Runtime Layer Swapping and KV Cache Resizing—0
LatentLLM: Attention-Aware Joint Tensor Compression—0
Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing—0
Edge-First Language Model Inference: Models, Metrics, and Tradeoffs—0
On Multilingual Encoder Language Model Compression for Low-Resource Languages—0
Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models—0
RanDeS: Randomized Delta Superposition for Multi-Model CompressionCode0
Low-Complexity Inference in Continual Learning via Compressed Knowledge Transfer—0
KDH-MLTC: Knowledge Distillation for Healthcare Multi-Label Text Classification—0
Semantic Retention and Extreme Compression in LLMs: Can We Have Both?—0
Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning—0
Edge-Optimized Deep Learning & Pattern Recognition Techniques for Non-Intrusive Load Monitoring of Energy Time Series—0
Onboard Optimization and Learning: A Survey—0
Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques—0
Radio: Rate-Distortion Optimization for Large Language Model Compression—0
Smart Environmental Monitoring of Marine Pollution using Edge AI—0
Towards Faster and More Compact Foundation Models for Molecular Property PredictionCode0
Low-Rank Matrix Approximation for Neural Network Compression—0
On-Device Qwen2.5: Efficient LLM Inference with Model Compression and Hardware Acceleration—0
Show:102550
← PrevPage 10 of 55Next →
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