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 801–850 of 4925 papers

TitleStatusHype
MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling QuantizationCode1
QuanCrypt-FL: Quantized Homomorphic Encryption with Pruning for Secure Federated Learning—0
Green My LLM: Studying the key factors affecting the energy consumption of code assistants—0
Saliency Assisted Quantization for Neural Networks—0
Compressive Spectrum Sensing with 1-bit ADCs—0
Scaling Laws for PrecisionCode2
BitNet a4.8: 4-bit Activations for 1-bit LLMsCode4
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion ModelsCode4
Multi-bit Distributed Detection of Sparse Stochastic Signals over Error-Prone Reporting Channels—0
Interactions Across Blocks in Post-Training Quantization of Large Language Models—0
An Edge Computing-Based Solution for Real-Time Leaf Disease Classification using Thermal ImagingCode0
Sum Rate Maximization in the Constant Envelope MIMO Downlink with the RZF Precoder—0
Hybrid Beamforming for Integrated Sensing and Communications With Low Resolution DACs—0
Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money LaunderingCode1
Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety AlignmentCode0
Transferable Sequential Recommendation via Vector Quantized Meta Learning—0
"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization—0
Addressing Representation Collapse in Vector Quantized Models with One Linear LayerCode3
BF-IMNA: A Bit Fluid In-Memory Neural Architecture for Neural Network Acceleration—0
VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector QuantizationCode1
Conformalized High-Density Quantile Regression via Dynamic Prototypes-based Probability Density EstimationCode0
Fundamental Trade-offs in Quantized Hybrid Radar Fusion: A CRB-Rate Perspective—0
Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval—0
Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series ClassificationCode1
Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model—0
ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs—0
BitStack: Any-Size Compression of Large Language Models in Variable Memory EnvironmentsCode1
ALISE: Accelerating Large Language Model Serving with Speculative Scheduling—0
Accelerated AI Inference via Dynamic Execution Methods—0
A Comprehensive Study on Quantization Techniques for Large Language Models—0
GWQ: Gradient-Aware Weight Quantization for Large Language Models—0
APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm—0
ELMGS: Enhancing memory and computation scaLability through coMpression for 3D Gaussian Splatting—0
IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion ModelsCode1
Data Generation for Hardware-Friendly Post-Training QuantizationCode3
HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation—0
The Impact of Inference Acceleration Strategies on Bias of LLMsCode0
NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural NetworksCode2
EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation—0
Logarithmically Quantized Distributed Optimization over Dynamic Multi-Agent Networks—0
Vector Quantization Prompting for Continual LearningCode1
Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector QuantizationCode0
Unleashing Dynamic Range and Resolution in Unlimited Sensing Framework via Novel Hardware—0
DQRM: Deep Quantized Recommendation ModelsCode0
You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models—0
A Survey of Small Language Models—0
Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth QuantizationCode0
COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 TrainingCode3
Learning ID-free Item Representation with Token Crossing for Multimodal Recommendation—0
Sliding DFT-based Signal Recovery for Modulo ADC with 1-bit Folding Information—0
Show:102550
← PrevPage 17 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