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 1–50 of 1356 papers

TitleStatusHype
SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion TransformerCode9
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained TransformersCode7
A Survey on Knowledge Distillation of Large Language ModelsCode5
LLM Inference Unveiled: Survey and Roofline Model InsightsCode4
Efficient Reasoning Models: A SurveyCode3
SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model CompressionCode3
ZipNN: Lossless Compression for AI ModelsCode3
ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language ModelsCode3
Compact 3D Gaussian Splatting for Static and Dynamic Radiance FieldsCode3
SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model CompressionCode3
LightGNN: Simple Graph Neural Network for RecommendationCode2
MaskLLM: Learnable Semi-Structured Sparsity for Large Language ModelsCode2
Q-DiT: Accurate Post-Training Quantization for Diffusion TransformersCode2
MoA: Mixture of Sparse Attention for Automatic Large Language Model CompressionCode2
Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator DesignCode2
PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-TuningCode2
QuEST: Low-bit Diffusion Model Quantization via Efficient Selective FinetuningCode2
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object DetectionCode2
Compact 3D Gaussian Representation for Radiance FieldCode2
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language ModelsCode2
Diffusion Models for Image Restoration and Enhancement -- A Comprehensive SurveyCode2
Compressing Volumetric Radiance Fields to 1 MBCode2
On-Device Domain GeneralizationCode2
Towards Lightweight Super-Resolution with Dual Regression LearningCode2
Learning Student Networks in the WildCode2
Fast convolutional neural networks on FPGAs with hls4mlCode2
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New OutlooksCode2
Well-Read Students Learn Better: On the Importance of Pre-training Compact ModelsCode2
AMC: AutoML for Model Compression and Acceleration on Mobile DevicesCode2
Data-Free Knowledge Distillation for Deep Neural NetworksCode2
FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix ApproximationCode1
Consistent Quantity-Quality Control across Scenes for Deployment-Aware Gaussian SplattingCode1
Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical MappingCode1
Forget the Data and Fine-Tuning! Just Fold the Network to CompressCode1
DarwinLM: Evolutionary Structured Pruning of Large Language ModelsCode1
Activation-Informed Merging of Large Language ModelsCode1
A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor FusionCode1
Merging Feed-Forward Sublayers for Compressed TransformersCode1
CoA: Towards Real Image Dehazing via Compression-and-AdaptationCode1
Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LNCode1
LLMCBench: Benchmarking Large Language Model Compression for Efficient DeploymentCode1
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary SearchCode1
SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight CompressionCode1
QT-DoG: Quantization-aware Training for Domain GeneralizationCode1
Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model CompressionCode1
Search for Efficient Large Language ModelsCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Hyper-Compression: Model Compression via HyperfunctionCode1
Localize-and-Stitch: Efficient Model Merging via Sparse Task ArithmeticCode1
Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and TransformersCode1
Show:102550
← PrevPage 1 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