SOTAVerified

Quantization

Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).

Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 701–750 of 4925 papers

TitleStatusHype
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion ModelsCode1
A Little Bit More: Bitplane-Wise Bit-Depth RecoveryCode1
Lossy Image Compression with Quantized Hierarchical VAEsCode1
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language GenerationCode1
Fast Lossless Neural Compression with Integer-Only Discrete FlowsCode1
PROFIT: A Novel Training Method for sub-4-bit MobileNet ModelsCode1
Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike FluctuationsCode1
Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural NetworksCode1
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial LearningCode1
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer MergingCode1
Continual Learning via Bit-Level Information PreservingCode1
Lossy Compression with Gaussian DiffusionCode1
Evaluation and Optimization of Gradient Compression for Distributed Deep LearningCode1
Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and ToolboxCode1
Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware AttentionCode1
Examining Post-Training Quantization for Mixture-of-Experts: A BenchmarkCode1
BRECQ: Pushing the Limit of Post-Training Quantization by Block ReconstructionCode1
ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint ShrinkingCode1
Context-aware Communication for Multi-agent Reinforcement LearningCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Confounding Tradeoffs for Neural Network QuantizationCode1
Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language ModelsCode1
Automatic Perturbation Analysis for Scalable Certified Robustness and BeyondCode1
Exploring Quantization for Efficient Pre-Training of Transformer Language ModelsCode1
ConveRT: Efficient and Accurate Conversational Representations from TransformersCode1
Broken Neural Scaling LawsCode1
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel ApproachCode1
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
Integer-only Zero-shot Quantization for Efficient Speech RecognitionCode1
QCM-SGM+: Improved Quantized Compressed Sensing With Score-Based Generative ModelsCode1
AlignQ: Alignment Quantization With ADMM-Based Correlation PreservationCode1
Conditional Coding and Variable Bitrate for Practical Learned Video CodingCode1
CABM: Content-Aware Bit Mapping for Single Image Super-Resolution Network with Large InputCode1
COMQ: A Backpropagation-Free Algorithm for Post-Training QuantizationCode1
Compression with Bayesian Implicit Neural RepresentationsCode1
Adaptive Gradient Quantization for Data-Parallel SGDCode1
Fast Nearest Convolution for Real-Time Efficient Image Super-ResolutionCode1
CADyQ: Content-Aware Dynamic Quantization for Image Super-ResolutionCode1
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
FastText.zip: Compressing text classification modelsCode1
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
LogicNets: Co-Designed Neural Networks and Circuits for Extreme-Throughput ApplicationsCode1
Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM CompressionCode1
LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy PreservationCode1
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-ResolutionCode1
CE-VAE: Capsule Enhanced Variational AutoEncoder for Underwater Image EnhancementCode1
Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and CompressionCode1
CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in SpaceCode1
Dataset Quantization with Active Learning based Adaptive SamplingCode1
Compressing LLMs: The Truth is Rarely Pure and Never SimpleCode1
Show:102550
← PrevPage 15 of 99Next →
All datasetsImageNetCIFAR-10Wiki-40BAgeDB-30CFP-FPCOCO (Common Objects in Context)IJB-BIJB-CKnowledge-based:LFW

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FQ-ViT (ViT-L)Top-1 Accuracy (%)85.03—Unverified
2FQ-ViT (ViT-B)Top-1 Accuracy (%)83.31—Unverified
3FQ-ViT (Swin-B)Top-1 Accuracy (%)82.97—Unverified
4FQ-ViT (Swin-S)Top-1 Accuracy (%)82.71—Unverified
5FQ-ViT (DeiT-B)Top-1 Accuracy (%)81.2—Unverified
6FQ-ViT (Swin-T)Top-1 Accuracy (%)80.51—Unverified
7FQ-ViT (DeiT-S)Top-1 Accuracy (%)79.17—Unverified
8Xception W8A8Top-1 Accuracy (%)78.97—Unverified
9ADLIK-MO-ResNet50-W4A4Top-1 Accuracy (%)77.88—Unverified
10ADLIK-MO-ResNet50-W3A4Top-1 Accuracy (%)77.34—Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_3MAP160,327.04—Unverified
2DTQMAP0.79—Unverified
#ModelMetricClaimedVerifiedStatus
1OutEffHop-Bert_basePerplexity6.3—Unverified
2OutEffHop-Bert_basePerplexity6.21—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy98.13—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy92.92—Unverified
#ModelMetricClaimedVerifiedStatus
1SSD ResNet50 V1 FPN 640x640MAP34.3—Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-495.13—Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-496.38—Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_5All84,809,664—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy99.8—Unverified