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 3301–3350 of 4925 papers

TitleStatusHype
What Does a One-Bit Quanta Image Sensor Offer?—0
What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data Pretrained Language Models—0
An Evaluation of Memory Optimization Methods for Training Neural Networks—0
What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation—0
When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization—0
When Bio-Inspired Computing meets Deep Learning: Low-Latency, Accurate, & Energy-Efficient Spiking Neural Networks from Artificial Neural Networks—0
When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models—0
When Reasoning Meets Compression: Benchmarking Compressed Large Reasoning Models on Complex Reasoning Tasks—0
Where Should We Begin? A Low-Level Exploration of Weight Initialization Impact on Quantized Behaviour of Deep Neural Networks—0
Which Space Partitioning Tree to Use for Search?—0
DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition—0
Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks—0
Wide Flat Minimum Watermarking for Robust Ownership Verification of GANs—0
Widening and Squeezing: Towards Accurate and Efficient QNNs—0
Winning Amazon KDD Cup'24—0
Wireless End-to-End Image Transmission System using Semantic Communications—0
Wireless Quantized Federated Learning: A Joint Computation and Communication Design—0
Within-basket Recommendation via Neural Pattern Associator—0
Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence—0
Witten-type topological field theory of self-organized criticality for stochastic neural networks—0
WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More—0
Word-based Domain Adaptation for Neural Machine Translation—0
Work in Progress: Linear Transformers for TinyML—0
WrapNet: Neural Net Inference with Ultra-Low-Resolution Arithmetic—0
WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic—0
WRPN: Training and Inference using Wide Reduced-Precision Networks—0
WSMN: An optimized multipurpose blind watermarking in Shearlet domain using MLP and NSGA-II—0
WSNet: Compact and Efficient Networks Through Weight Sampling—0
WSNet: Learning Compact and Efficient Networks with Weight Sampling—0
Wyner-Ziv Gradient Compression for Federated Learning—0
XCAT -- Lightweight Quantized Single Image Super-Resolution using Heterogeneous Group Convolutions and Cross Concatenation—0
XNORBIN: A 95 TOp/s/W Hardware Accelerator for Binary Convolutional Neural Networks—0
XNOR-Net++: Improved Binary Neural Networks—0
YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers—0
You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models—0
YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving—0
Consistent Signal Reconstruction from Streaming Multivariate Time Series—0
Zero-Delay Gaussian Joint Source-Channel Coding for the Interference Channel—0
FDC: Fast KV Dimensionality Compression for Efficient LLM Inference—0
ZeRO++: Extremely Efficient Collective Communication for Giant Model Training—0
ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats—0
ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers—0
Zero-shot Adversarial Quantization—0
Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization—0
Zero-shot Quantization: A Comprehensive Survey—0
Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models—0
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity—0
ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning—0
ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification—0
ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters—0
Show:102550
← PrevPage 67 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