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 1201–1250 of 4925 papers

TitleStatusHype
Timestep-Aware Correction for Quantized Diffusion Models—0
Low-latency machine learning FPGA accelerator for multi-qubit-state discrimination—0
OSPC: Artificial VLM Features for Hateful Meme Detection—0
Edge AI-Enabled Chicken Health Detection Based on Enhanced FCOS-Lite and Knowledge Distillation—0
Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations—0
Fisher-aware Quantization for DETR Detectors with Critical-category Objectives—0
How Does Quantization Affect Multilingual LLMs?—0
Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment—0
ADFQ-ViT: Activation-Distribution-Friendly Post-Training Quantization for Vision Transformers—0
Unified Anomaly Detection methods on Edge Device using Knowledge Distillation and Quantization—0
GPTQT: Quantize Large Language Models Twice to Push the Efficiency—0
SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic—0
QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid DevicesCode1
PQCache: Product Quantization-based KVCache for Long Context LLM Inference—0
Linear and Nonlinear MMSE Estimation in One-Bit Quantized Systems under a Gaussian Mixture Prior—0
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable ApproachesCode2
Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural NetworksCode0
Exploring FPGA designs for MX and beyond—0
Beyond Throughput and Compression Ratios: Towards High End-to-end Utility of Gradient Compression—0
NeuroNAS: Enhancing Efficiency of Neuromorphic In-Memory Computing for Intelligent Mobile Agents through Hardware-Aware Spiking Neural Architecture Search—0
Toward a Diffusion-Based Generalist for Dense Vision Tasks—0
Rateless Stochastic Coding for Delay-Constrained Semantic Communication—0
Deep Fusion Model for Brain Tumor Classification Using Fine-Grained Gradient Preservation—0
LLMEasyQuant: Scalable Quantization for Parallel and Distributed LLM InferenceCode1
Reliable edge machine learning hardware for scientific applications—0
Fronthaul Quantization-Aware MU-MIMO Precoding for Sum Rate Maximization—0
OutlierTune: Efficient Channel-Wise Quantization for Large Language Models—0
Efficient course recommendations with T5-based ranking and summarizationCode0
MCNC: Manifold Constrained Network Compression—0
A Quantization-based Technique for Privacy Preserving Distributed Learning—0
FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantization—0
Differential error feedback for communication-efficient decentralized learning—0
ViT-1.58b: Mobile Vision Transformers in the 1-bit EraCode1
T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on EdgeCode4
Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-LevelsCode0
CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization—0
Q-DiT: Accurate Post-Training Quantization for Diffusion TransformersCode2
BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks—0
Approximate DCT and Quantization Techniques for Energy-Constrained Image Sensors—0
Leveraging Knowledge Distillation for Lightweight Skin Cancer Classification: Balancing Accuracy and Computational Efficiency—0
Reducing the Memory Footprint of 3D Gaussian Splatting—0
Compensate Quantization Errors: Make Weights Hierarchical to Compensate Each Other—0
ShadowLLM: Predictor-based Contextual Sparsity for Large Language ModelsCode1
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer MergingCode1
Received Power Maximization Using Nonuniform Discrete Phase Shifts for RISs With a Limited Phase Range—0
Towards Real-Time Neural Volumetric Rendering on Mobile Devices: A Measurement Study—0
EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and VotingCode2
HLQ: Fast and Efficient Backpropagation via Hadamard Low-rank Quantization—0
FLoCoRA: Federated learning compression with low-rank adaptationCode0
Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE—0
Show:102550
← PrevPage 25 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