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 151–200 of 4925 papers

TitleStatusHype
Visual Autoregressive Modeling for Image Super-ResolutionCode2
GaussianToken: An Effective Image Tokenizer with 2D Gaussian SplattingCode2
OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution FittingCode2
Lossless Compression of Vector IDs for Approximate Nearest Neighbor SearchCode2
Qinco2: Vector Compression and Search with Improved Implicit Neural CodebooksCode2
Optimizing Edge AI: A Comprehensive Survey on Data, Model, and System StrategiesCode2
MBQ: Modality-Balanced Quantization for Large Vision-Language ModelsCode2
Preventing Local Pitfalls in Vector Quantization via Optimal TransportCode2
QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint VideosCode2
MotionLLaMA: A Unified Framework for Motion Synthesis and ComprehensionCode2
PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-ResolutionCode2
Efficient Video Face Enhancement with Enhanced Spatial-Temporal ConsistencyCode2
Quantized symbolic time series approximationCode2
SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor SearchCode2
The Super Weight in Large Language ModelsCode2
Scaling Laws for PrecisionCode2
NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural NetworksCode2
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor SearchCode2
SimLayerKV: A Simple Framework for Layer-Level KV Cache ReductionCode2
Quamba: A Post-Training Quantization Recipe for Selective State Space ModelsCode2
When Attention Sink Emerges in Language Models: An Empirical ViewCode2
Q-VLM: Post-training Quantization for Large Vision-Language ModelsCode2
MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains MoreCode2
PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models QuantizationCode2
A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image GenerationCode2
INT-FlashAttention: Enabling Flash Attention for INT8 QuantizationCode2
Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor SearchCode2
S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-trainingCode2
Training-Free Activation Sparsity in Large Language ModelsCode2
MobileQuant: Mobile-friendly Quantization for On-device Language ModelsCode2
Efficient Autoregressive Audio Modeling via Next-Scale PredictionCode2
Palu: Compressing KV-Cache with Low-Rank ProjectionCode2
Temporal Feature Matters: A Framework for Diffusion Model QuantizationCode2
Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at ScaleCode2
GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook RetrievalCode2
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable ApproachesCode2
Q-DiT: Accurate Post-Training Quantization for Diffusion TransformersCode2
EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and VotingCode2
Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%Code2
QQQ: Quality Quattuor-Bit Quantization for Large Language ModelsCode2
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language ModelsCode2
Low-Rank Quantization-Aware Training for LLMsCode2
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMsCode2
Compressing Large Language Models using Low Rank and Low Precision DecompositionCode2
LoQT: Low-Rank Adapters for Quantized PretrainingCode2
TerDiT: Ternary Diffusion Models with TransformersCode2
SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language ModelsCode2
RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor SearchCode2
Imp: Highly Capable Large Multimodal Models for Mobile DevicesCode2
PTQ4SAM: Post-Training Quantization for Segment AnythingCode2
Show:102550
← PrevPage 4 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