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 576–600 of 1356 papers

TitleStatusHype
Frustratingly Easy Model Ensemble for Abstractive Summarization—0
From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models—0
Fundamental Limits of Communication Efficiency for Model Aggregation in Distributed Learning: A Rate-Distortion Approach—0
From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs—0
GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization—0
GECKO: Reconciling Privacy, Accuracy and Efficiency in Embedded Deep Learning—0
GeneCAI: Genetic Evolution for Acquiring Compact AI—0
Conditional Teacher-Student Learning—0
Conditional Generative Data-free Knowledge Distillation—0
From Cloud to Edge: Rethinking Generative AI for Low-Resource Design Challenges—0
A Survey on Green Deep Learning—0
Convolutional Neural Network Compression Based on Low-Rank Decomposition—0
From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks—0
Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models—0
Fragile Mastery: Are Domain-Specific Trade-Offs Undermining On-Device Language Models?—0
Conditional Automated Channel Pruning for Deep Neural Networks—0
A flexible, extensible software framework for model compression based on the LC algorithm—0
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks—0
HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks—0
ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval—0
GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference—0
Gradient-Free Structured Pruning with Unlabeled Data—0
Atleus: Accelerating Transformers on the Edge Enabled by 3D Heterogeneous Manycore Architectures—0
Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks—0
Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations—0
Show:102550
← PrevPage 24 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