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 301–325 of 4925 papers

TitleStatusHype
A Refined Analysis of Massive Activations in LLMsCode1
VADMamba: Exploring State Space Models for Fast Video Anomaly DetectionCode1
LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy PreservationCode1
QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the EdgeCode1
PCGS: Progressive Compression of 3D Gaussian SplattingCode1
QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video GenerationCode1
QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-ResolutionCode1
RSQ: Learning from Important Tokens Leads to Better Quantized LLMsCode1
Oscillation-Reduced MXFP4 Training for Vision TransformersCode1
Towards Lossless Implicit Neural Representation via Bit Plane DecompositionCode1
Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and CompressionCode1
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language ModelsCode1
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
CISSIR: Beam Codebooks with Self-Interference Reduction Guarantees for Integrated Sensing and Communication Beyond 5GCode1
SQ-GAN: Semantic Image Communications Using Masked Vector QuantizationCode1
Cache Me If You Must: Adaptive Key-Value Quantization for Large Language ModelsCode1
Quantized Spike-driven TransformerCode1
D^2-DPM: Dual Denoising for Quantized Diffusion Probabilistic ModelsCode1
kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors SearchCode1
DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion ModelsCode1
HALO: Hadamard-Assisted Lower-Precision Optimization for LLMsCode1
PTQ4VM: Post-Training Quantization for Visual MambaCode1
An Automatic Graph Construction Framework based on Large Language Models for RecommendationCode1
Hierarchical Vector Quantization for Unsupervised Action SegmentationCode1
Show:102550
← PrevPage 13 of 197Next →
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