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 401–450 of 4925 papers

TitleStatusHype
AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model—0
Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations—0
BHViT: Binarized Hybrid Vision TransformerCode2
Q&C: When Quantization Meets Cache in Efficient Image GenerationCode0
BdSLW401: Transformer-Based Word-Level Bangla Sign Language Recognition Using Relative Quantization Encoding (RQE)—0
DILEMMA: Joint LLM Quantization and Distributed LLM Inference Over Edge Computing Systems—0
Regularization-based Framework for Quantization-, Fault- and Variability-Aware Training—0
DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models—0
Cauchy-Schwarz RegularizersCode0
KurTail : Kurtosis-based LLM Quantization—0
Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text—0
RSQ: Learning from Important Tokens Leads to Better Quantized LLMsCode1
Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language ModelCode0
MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations—0
Towards Lossless Implicit Neural Representation via Bit Plane DecompositionCode1
Strong Solutions and Quantization-Based Numerical Schemes for a Class of Non-Markovian Volatility Models—0
Oscillation-Reduced MXFP4 Training for Vision TransformersCode1
UniTok: A Unified Tokenizer for Visual Generation and UnderstandingCode4
Speculative Decoding and Beyond: An In-Depth Review of Techniques—0
Transformer-Based Nonlinear Transform Coding for Multi-Rate CSI Compression in MIMO-OFDM Systems—0
Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models—0
HALO: Hardware-aware quantization with low critical-path-delay weights for LLM acceleration—0
On the Privacy-Preserving Properties of Spiking Neural Networks with Unique Surrogate Gradients and Quantization Levels—0
Memory-Free and Parallel Computation for Quantized Spiking Neural Networks—0
Compressing Language Models for Specialized Domains—0
Task-Driven Semantic Quantization and Imitation Learning for Goal-Oriented Communications—0
Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs—0
Compression Scaling Laws:Unifying Sparsity and Quantization—0
Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification—0
Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration—0
Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and CompressionCode1
A 2-bit Wideband 5G mm-Wave RIS with Low Side Lobe Levels and no Quantization Lobe—0
Verification of Bit-Flip Attacks against Quantized Neural Networks—0
Speech Enhancement Using Continuous Embeddings of Neural Audio Codec—0
Q-PETR: Quant-aware Position Embedding Transformation for Multi-View 3D Object Detection—0
When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models—0
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention—0
Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements—0
FD-LSCIC: Frequency Decomposition-based Learned Screen Content Image Compression—0
Interleaved Block-based Learned Image Compression with Feature Enhancement and Quantization Error Compensation—0
Hardware-Friendly Static Quantization Method for Video Diffusion Transformers—0
More for Keys, Less for Values: Adaptive KV Cache Quantization—0
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMsCode3
Efficient AI in Practice: Training and Deployment of Efficient LLMs for Industry Applications—0
A General Error-Theoretical Analysis Framework for Constructing Compression Strategies—0
Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language ModelsCode2
Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language ModelsCode0
A^2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization—0
Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative AnalysisCode0
Show:102550
← PrevPage 9 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