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 1001–1050 of 4925 papers

TitleStatusHype
Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to GiantCode0
LASERS: LAtent Space Encoding for Representations with Sparsity for Generative Modeling—0
Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor SearchCode2
Forearm Ultrasound based Gesture Recognition on Edge—0
Language Models and Retrieval Augmented Generation for Automated Structured Data Extraction from Diagnostic Reports—0
Improving Statistical Significance in Human Evaluation of Automatic Metrics via Soft Pairwise Accuracy—0
MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation—0
Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare—0
Robust Training of Neural Networks at Arbitrary Precision and Sparsity—0
S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-trainingCode2
Investigating Disentanglement in a Phoneme-level Speech Codec for Prosody Modeling—0
Dequantization of a signal from two parallel quantized observations—0
DiTAS: Quantizing Diffusion Transformers via Enhanced Activation SmoothingCode1
Efficient and Reliable Vector Similarity Search Using Asymmetric Encoding with NAND-Flash for Many-Class Few-Shot Learning—0
Distributed Convolutional Neural Network Training on Mobile and Edge Clusters—0
STORE: Streamlining Semantic Tokenization and Generative Recommendation with A Single LLM—0
Adaptive Error-Bounded Hierarchical Matrices for Efficient Neural Network Compression—0
NVRC: Neural Video Representation Compression—0
AgileIR: Memory-Efficient Group Shifted Windows Attention for Agile Image Restoration—0
Rate-Constrained Quantization for Communication-Efficient Federated Learning—0
Distributed Optimization with Finite Bit Adaptive Quantization for Efficient Communication and Precision Enhancement—0
ECG Biometric Authentication Using Self-Supervised Learning for IoT Edge Sensors—0
BigCodec: Pushing the Limits of Low-Bitrate Neural Speech CodecCode3
SGC-VQGAN: Towards Complex Scene Representation via Semantic Guided Clustering Codebook—0
Estimating the Completeness of Discrete Speech Units—0
TriplePlay: Enhancing Federated Learning with CLIP for Non-IID Data and Resource Efficiency—0
BBS: Bi-directional Bit-level Sparsity for Deep Learning AccelerationCode1
Blind-Adaptive Quantizers—0
OPAL: Outlier-Preserved Microscaling Quantization Accelerator for Generative Large Language Models—0
Recursive Quantization for L_2 Stabilization of a Finite Capacity Stochastic Control Loop with Intermittent State Observations—0
WaterMAS: Sharpness-Aware Maximization for Neural Network Watermarking—0
Investigating Privacy Bias in Training Data of Language Models—0
LAST: Language Model Aware Speech Tokenization—0
Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model—0
Learning Task-Based Trainable Neuromorphic ADCs via Power-Aware Distillation—0
Gaussian Rate-Distortion-Perception Coding and Entropy-Constrained Scalar Quantization—0
Task-Oriented Communication for Graph Data: A Graph Information Bottleneck Approach—0
CoAst: Validation-Free Contribution Assessment for Federated Learning based on Cross-Round Valuation—0
Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearables—0
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Foundations of Large Language Model Compression -- Part 1: Weight QuantizationCode0
Robust Clustering on High-Dimensional Data with Stochastic QuantizationCode0
Compressing VAE-Based Out-of-Distribution Detectors for Embedded Deployment—0
VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector QuantizationCode1
One-Index Vector Quantization Based Adversarial Attack on Image Classification—0
Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networks—0
Enhancing Multi-Stream Beamforming Through CQIs For 5G NR FDD Massive MIMO Communications: A Tuning-Free Scheme—0
TinyAgent: Function Calling at the EdgeCode3
Federated Aggregation of Mallows Rankings: A Comparative Analysis of Borda and Lehmer Coding—0
Hyper-Compression: Model Compression via HyperfunctionCode1
Show:102550
← PrevPage 21 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