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 1151–1200 of 4925 papers

TitleStatusHype
Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients—0
StoX-Net: Stochastic Processing of Partial Sums for Efficient In-Memory Computing DNN AcceleratorsCode0
GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook RetrievalCode2
Mamba-PTQ: Outlier Channels in Recurrent Large Language Models—0
Rate-Distortion-Cognition Controllable Versatile Neural Image Compression—0
Co-Designing Binarized Transformer and Hardware Accelerator for Efficient End-to-End Edge Deployment—0
Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors—0
Exploring Quantization for Efficient Pre-Training of Transformer Language ModelsCode1
Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large ModelsCode1
NITRO-D: Native Integer-only Training of Deep Convolutional Neural NetworksCode0
QVD: Post-training Quantization for Video Diffusion Models—0
LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling MatricesCode0
Fast Matrix Multiplications for Lookup Table-Quantized LLMsCode3
Quality Scalable Quantization Methodology for Deep Learning on Edge—0
SEMINAR: Search Enhanced Multi-modal Interest Network and Approximate Retrieval for Lifelong Sequential Recommendation—0
Qwen2 Technical ReportCode13
Quantized Prompt for Efficient Generalization of Vision-Language ModelsCode0
LeanQuant: Accurate Large Language Model Quantization with Loss-Error-Aware Grid—0
A Bag of Tricks for Scaling CPU-based Deep FFMs to more than 300m Predictions per Second—0
One-Bit MIMO Detection: From Global Maximum-Likelihood Detector to Amplitude Retrieval Approach—0
Semi-supervised 3D Object Detection with PatchTeacher and PillarMixCode0
PSC: Posterior Sampling-Based CompressionCode1
Optimization of DNN-based speaker verification model through efficient quantization technique—0
Accuracy is Not All You Need—0
On Exact Bit-level Reversible Transformers Without Changing ArchitecturesCode1
Distributed Deep Reinforcement Learning Based Gradient Quantization for Federated Learning Enabled Vehicle Edge Computing—0
ADMM Based Semi-Structured Pattern Pruning Framework For Transformer—0
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisionCode12
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank GradientsCode5
Autoregressive Speech Synthesis without Vector Quantization—0
Applying generative neural networks for fast simulations of the ALICE (CERN) experimentCode0
EfficientQAT: Efficient Quantization-Aware Training for Large Language ModelsCode3
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation QuantizationCode1
Dataset Quantization with Active Learning based Adaptive SamplingCode1
ERQ: Error Reduction for Post-Training Quantization of Vision Transformers—0
CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic TokensCode11
Ternary Spike-based Neuromorphic Signal Processing System—0
CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTsCode1
OvSW: Overcoming Silent Weights for Accurate Binary Neural NetworksCode1
Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT—0
Quantizing YOLOv7: A Comprehensive Study—0
Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM CompressionCode0
Balance of Number of Embedding and their Dimensions in Vector Quantization—0
ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters—0
Hybrid Receiver Design for Massive MIMO-OFDM with Low-Resolution ADCs and Oversampling—0
SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based SpikingCode1
Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation MapsCode0
The Impact of Quantization and Pruning on Deep Reinforcement Learning Models—0
Joint Beamforming Design and Bit Allocation in Massive MIMO with Resolution-Adaptive ADCs—0
Low-latency machine learning FPGA accelerator for multi-qubit-state discrimination—0
Show:102550
← PrevPage 24 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