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 2001–2050 of 4925 papers

TitleStatusHype
Norm Tweaking: High-performance Low-bit Quantization of Large Language Models—0
Bandwidth-efficient Inference for Neural Image Compression—0
RobustEdge: Low Power Adversarial Detection for Cloud-Edge Systems—0
QuantEase: Optimization-based Quantization for Language Models—0
On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks—0
A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking—0
Compressing Vision Transformers for Low-Resource Visual LearningCode0
On the fly Deep Neural Network Optimization Control for Low-Power Computer Vision—0
Softmax Bias Correction for Quantized Generative Models—0
eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models—0
Few shot font generation via transferring similarity guided global style and quantization local styleCode1
RepCodec: A Speech Representation Codec for Speech TokenizationCode1
Learning Category Trees for ID-Based Recommendation: Exploring the Power of Differentiable Vector QuantizationCode0
SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language ModelsCode2
FPTQ: Fine-grained Post-Training Quantization for Large Language Models—0
Implementation and Evaluation of Physical Layer Key Generation on SDR based LoRa Platform—0
Continual Learning for Generative Retrieval over Dynamic CorporaCode0
Uncovering the Hidden Cost of Model CompressionCode0
On-Device Learning with Binary Neural Networks—0
Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message PropagationCode0
Maestro: Uncovering Low-Rank Structures via Trainable DecompositionCode0
MEMORY-VQ: Compression for Tractable Internet-Scale Memory—0
VQ-Font: Few-Shot Font Generation with Structure-Aware Enhancement and QuantizationCode1
Efficient Learned Lossless JPEG Recompression—0
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language ModelsCode2
A2Q: Accumulator-Aware Quantization with Guaranteed Overflow AvoidanceCode0
Quantized distributed Nash equilibrium seeking under DoS attacks—0
Hybrid noise shaping for audio coding using perfectly overlapped window—0
Robust open-set classification for encrypted traffic fingerprintingCode0
Consistent Signal Reconstruction from Streaming Multivariate Time Series—0
Compressed Models Decompress Race Biases: What Quantized Models Forget for Fair Face Recognition—0
Distributed Energy Resource Management: All-Time Resource-Demand Feasibility, Delay-Tolerance, Nonlinearity, and Beyond—0
Towards Clip-Free Quantized Super-Resolution Networks: How to Tame Representative Images—0
Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language ModelsCode1
Jumping through Local Minima: Quantization in the Loss Landscape of Vision TransformersCode1
QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection—0
Dataset QuantizationCode2
Sampling From Autoencoders' Latent Space via Quantization And Probability Mass Function Concepts—0
Quantization-based Optimization with Perspective of Quantum Mechanics—0
Analyzing Quantization in TVM—0
FunQuant: A R package to perform quantization in the context of rare events and time-consuming simulations—0
NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization for Continual LearningCode1
SHARK: A Lightweight Model Compression Approach for Large-scale Recommender Systems—0
ResQ: Residual Quantization for Video Perception—0
JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer—0
FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs—0
Precision and Recall Reject Curves for Classification—0
Characteristics of networks generated by kernel growing neural gasCode0
Gradient-Based Post-Training Quantization: Challenging the Status Quo—0
A Survey on Model Compression for Large Language Models—0
Show:102550
← PrevPage 41 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