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 1651–1700 of 4925 papers

TitleStatusHype
QERA: an Analytical Framework for Quantization Error Reconstruction—0
Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture Search—0
Variable Resolution Pixel Quantization for Low Power Machine Vision Application on Edge—0
Continuous Approximations for Improving Quantization Aware Training of LLMs—0
HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis—0
PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms—0
EXAQ: Exponent Aware Quantization For LLMs AccelerationCode0
Resource-aware Mixed-precision Quantization for Enhancing Deployability of Transformers for Time-series Forecasting on Embedded FPGAs—0
Generative Semantic Communication for Text-to-Speech Synthesis—0
MIMO Detection with Spatial Sigma-Delta ADCs: A Variational Bayesian Approach—0
SEAL: SEmantic-Augmented Imitation Learning via Language Model—0
Overcoming Representation Bias in Fairness-Aware data Repair using Optimal Transport—0
Remember and Recall: Associative-Memory-based Trajectory Prediction—0
Getting Free Bits Back from Rotational Symmetries in LLMs—0
Restorative Speech Enhancement: A Progressive Approach Using SE and Codec Modules—0
Trainable pruned ternary quantization for medical signal classification modelsCode0
Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging—0
STanH : Parametric Quantization for Variable Rate Learned Image Compression—0
Deep activity propagation via weight initialization in spiking neural networks—0
Aggressive Post-Training Compression on Extremely Large Language Models—0
Constraint Guided Model Quantization of Neural Networks—0
Accelerating PoT Quantization on Edge DevicesCode0
Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference—0
Mixed-Precision Embeddings for Large-Scale Recommendation Models—0
Quantized and Asynchronous Federated Learning—0
InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries—0
Efficient Federated Intrusion Detection in 5G ecosystem using optimized BERT-based modelCode0
Asymptotic tracking control of dynamic reference over homomorphically encrypted data with finite modulus—0
A method of using RSVD in residual calculation of LowBit GEMM—0
Heterogeneous quantization regularizes spiking neural network activity—0
Fronthaul-Constrained Distributed Radar Sensing—0
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior ModelsCode0
MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling—0
Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores—0
Digital and Hybrid Precoding Designs in Massive MIMO with Low-Resolution ADCsCode0
P4Q: Learning to Prompt for Quantization in Visual-language Models—0
Reinforcement Learning for Finite Space Mean-Field Type Games—0
A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms—0
Accumulator-Aware Post-Training Quantization—0
LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ—0
Using Random Codebooks for Audio Neural AutoEncoders—0
PTQ4RIS: Post-Training Quantization for Referring Image SegmentationCode0
AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned QuantizationCode0
A Formalization of Image Vectorization by Region Merging—0
Ultra-low latency quantum-inspired machine learning predictors implemented on FPGA—0
Communication and Energy Efficient Federated Learning using Zero-Order Optimization Technique—0
Twin Network Augmentation: A Novel Training Strategy for Improved Spiking Neural Networks and Efficient Weight Quantization—0
Disentanglement with Factor Quantized Variational AutoencodersCode0
Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity CluesCode0
SPAQ-DL-SLAM: Towards Optimizing Deep Learning-based SLAM for Resource-Constrained Embedded Platforms—0
Show:102550
← PrevPage 34 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