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 1051–1100 of 4925 papers

TitleStatusHype
Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization—0
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language ModelCode3
Identifying and Clustering Counter Relationships of Team Compositions in PvP Games for Efficient Balance AnalysisCode0
Approximately Invertible Neural Network for Learned Image Compression—0
VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers—0
On-device AI: Quantization-aware Training of Transformers in Time-Series—0
Blending Low and High-Level Semantics of Time Series for Better Masked Time Series Generation—0
The Uniqueness of LLaMA3-70B Series with Per-Channel Quantization—0
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMsCode0
On-Device Language Models: A Comprehensive ReviewCode0
Scalable Multivariate Fronthaul Quantization for Cell-Free Massive MIMO—0
Adaptive Resolution Inference (ARI): Energy-Efficient Machine Learning for Internet of Things—0
Training-Free Activation Sparsity in Large Language ModelsCode2
FusionSAM: Latent Space driven Segment Anything Model for Multimodal Fusion and Segmentation—0
1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bitCode1
Quantized neural network for complex hologram generation—0
Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized ModelsCode0
MobileQuant: Mobile-friendly Quantization for On-device Language ModelsCode2
Variational autoencoder-based neural network model compression—0
Revisiting DNN Training for Intermittently-Powered Energy-Harvesting Micro-Computers—0
Infrared Domain Adaptation with Zero-Shot Quantization—0
A Safe Self-evolution Algorithm for Autonomous Driving Based on Data-Driven Risk Quantification Model—0
Informational Embodiment: Computational role of information structure in codes and robots—0
Quantization-aware Matrix Factorization for Low Bit Rate Image CompressionCode1
DeepHQ: Learned Hierarchical Quantizer for Progressive Deep Image Coding—0
Jamba-1.5: Hybrid Transformer-Mamba Models at ScaleCode5
Matmul or No Matmal in the Era of 1-bit LLMs—0
MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language ModelsCode5
Disentangling segmental and prosodic factors to non-native speech comprehensibility—0
Hyperstroke: A Novel High-quality Stroke Representation for Assistive Artistic Drawing—0
Explore Cross-Codec Quality-Rate Convex Hulls Relation for Adaptive Streaming—0
ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language ModelsCode3
Efficient Autoregressive Audio Modeling via Next-Scale PredictionCode2
JPEG-LM: LLMs as Image Generators with Canonical Codec Representations—0
PQV-Mobile: A Combined Pruning and Quantization Toolkit to Optimize Vision Transformers for Mobile ApplicationsCode0
Analog Spiking Neuron in CMOS 28 nm Towards Large-Scale Neuromorphic Processors—0
Line Spectral Estimation with Unlimited Sensing—0
Prompt Tuning as User Inherent Profile Inference Machine—0
Low-Bitwidth Floating Point Quantization for Efficient High-Quality Diffusion Models—0
Computability of Classification and Deep Learning: From Theoretical Limits to Practical Feasibility through Quantization—0
RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization—0
SWIFT:A Scalable lightWeight Infrastructure for Fine-TuningCode11
Quantum-secure multiparty deep learning—0
Semantic-Enabled 6G Communication: A Task-oriented and Privacy-preserving Perspective—0
FDC: Fast KV Dimensionality Compression for Efficient LLM Inference—0
Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient AdaptationCode1
Compact 3D Gaussian Splatting for Static and Dynamic Radiance FieldsCode3
Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations—0
L3iTC at the FinLLM Challenge Task: Quantization for Financial Text Classification & Summarization—0
EC-Guide: A Comprehensive E-Commerce Guide for Instruction Tuning and QuantizationCode1
Show:102550
← PrevPage 22 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