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 301–350 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
Towards Lossless Implicit Neural Representation via Bit Plane DecompositionCode1
Oscillation-Reduced MXFP4 Training for Vision TransformersCode1
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
ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank ResidualsCode1
Relation-Guided Adversarial Learning for Data-free Knowledge TransferCode1
MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion ModelsCode1
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal DictionariesCode1
BiDM: Pushing the Limit of Quantization for Diffusion ModelsCode1
Temporally Compressed 3D Gaussian Splatting for Dynamic ScenesCode1
Improving Detail in Pluralistic Image Inpainting with Feature DequantizationCode1
DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined RotationCode1
Quantization without TearsCode1
MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling QuantizationCode1
Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money LaunderingCode1
VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector QuantizationCode1
Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series ClassificationCode1
BitStack: Any-Size Compression of Large Language Models in Variable Memory EnvironmentsCode1
IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion ModelsCode1
Vector Quantization Prompting for Continual LearningCode1
Catastrophic Failure of LLM Unlearning via QuantizationCode1
Residual vector quantization for KV cache compression in large language modelCode1
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary SearchCode1
Learning Graph Quantized TokenizersCode1
Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMsCode1
Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural NetworksCode1
SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight CompressionCode1
QT-DoG: Quantization-aware Training for Domain GeneralizationCode1
Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector QuantizationCode1
Show:102550
← PrevPage 7 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