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 1351–1400 of 4925 papers

TitleStatusHype
Athena: Efficient Block-Wise Post-Training Quantization for Large Language Models Using Second-Order Matrix Derivative Information—0
BiSup: Bidirectional Quantization Error Suppression for Large Language Models—0
OAC: Output-adaptive Calibration for Accurate Post-training Quantization—0
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language ModelsCode2
A rescaling-invariant Lipschitz bound based on path-metrics for modern ReLU network parameterizations—0
ASI++: Towards Distributionally Balanced End-to-End Generative Retrieval—0
Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs—0
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM CompressionCode5
LG-VQ: Language-Guided Codebook Learning—0
Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMsCode0
TerDiT: Ternary Diffusion Models with TransformersCode2
Distilling Vision-Language Pretraining for Efficient Cross-Modal Retrieval—0
MultiCast: Zero-Shot Multivariate Time Series Forecasting Using LLMs—0
Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising—0
Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative ModelsCode1
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models—0
Embedding Compression for Efficient Re-Identification—0
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token IdentificationCode1
AdpQ: A Zero-shot Calibration Free Adaptive Post Training Quantization Method for LLMs—0
Adaptive Wireless Image Semantic Transmission and Over-The-Air Testing—0
Communication-Efficient Federated Learning via Clipped Uniform QuantizationCode0
QGait: Toward Accurate Quantization for Gait Recognition with Binarized Input—0
Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers—0
eXmY: A Data Type and Technique for Arbitrary Bit Precision Quantization—0
Two Heads are Better Than One: Neural Networks Quantization with 2D Hilbert Curve-based Output Representation—0
ReALLM: A general framework for LLM compression and fine-tuning—0
Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities—0
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor AttacksCode1
On Image Registration and Subpixel Estimation—0
Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache CompressionCode0
RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor SearchCode2
Online Signature Recognition: A Biologically Inspired Feature Vector Splitting Approach—0
TinyM^2Net-V3: Memory-Aware Compressed Multimodal Deep Neural Networks for Sustainable Edge Deployment—0
Imp: Highly Capable Large Multimodal Models for Mobile DevicesCode2
Flattened one-bit stochastic gradient descent: compressed distributed optimization with controlled variance—0
Universal Joint Source-Channel Coding for Modulation-Agnostic Semantic Communication—0
Enhancing Perception Quality in Remote Sensing Image Compression via Invertible Neural Network—0
The Effect of Quantization in Federated Learning: A Rényi Differential Privacy Perspective—0
Deep Learning-Enabled One-Bit DoA EstimationCode1
Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and PrivacyCode1
Properties that allow or prohibit transferability of adversarial attacks among quantized networksCode0
Neural Speech Coding for Real-time Communications using Constant Bitrate Scalar Quantization—0
FDD Massive MIMO: How to Optimally Combine UL Pilot and Limited DL CSI Feedback?—0
VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling—0
Goal-oriented compression for L_p-norm-type goal functions: Application to power consumption scheduling—0
Post Training Quantization of Large Language Models with Microscaling Formats—0
Edge Intelligence Optimization for Large Language Model Inference with Batching and Quantization—0
Compression-Realized Deep Structural Network for Video Quality Enhancement—0
Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection—0
Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models—0
Show:102550
← PrevPage 28 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