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 1301–1350 of 4925 papers

TitleStatusHype
Spectral Codecs: Improving Non-Autoregressive Speech Synthesis with Spectrogram-Based Audio Codecs—0
Activation Map-based Vector Quantization for 360-degree Image Semantic Communication—0
Winner-takes-all learners are geometry-aware conditional density estimatorsCode0
Real-Time Spacecraft Pose Estimation Using Mixed-Precision Quantized Neural Network on COTS Reconfigurable MPSoCCode0
Proofread: Fixes All Errors with One Tap—0
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model—0
USM RNN-T model weights binarization—0
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity—0
VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise—0
Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement LearningCode1
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero OverheadCode1
Mixed-Precision Federated Learning via Multi-Precision Over-The-Air Aggregation—0
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video GenerationCode1
SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretrainingCode1
Toward Efficient Deep Spiking Neuron Networks:A Survey On Compression—0
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMsCode2
CE-VAE: Capsule Enhanced Variational AutoEncoder for Underwater Image EnhancementCode1
Log-Scale Quantization in Distributed First-Order Methods: Gradient-based Learning from Distributed Data—0
MagR: Weight Magnitude Reduction for Enhancing Post-Training QuantizationCode1
Privacy-Aware Randomized Quantization via Linear ProgrammingCode0
Effective Interplay between Sparsity and Quantization: From Theory to Practice—0
Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs—0
Locking Machine Learning Models into Hardware—0
LCQ: Low-Rank Codebook based Quantization for Large Language Models—0
An Efficient Network with Novel Quantization Designed for Massive MIMO CSI Feedback—0
S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs—0
HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization—0
P^2-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision TransformerCode1
One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments—0
CV-VAE: A Compatible Video VAE for Latent Generative Video ModelsCode3
Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encoder—0
Compressing Large Language Models using Low Rank and Low Precision DecompositionCode2
4-bit Shampoo for Memory-Efficient Network TrainingCode1
LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models—0
I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models—0
SLMRec: Distilling Large Language Models into Small for Sequential RecommendationCode1
Exploiting LLM QuantizationCode1
The Binary Quantized Neural Network for Dense Prediction via Specially Designed Upsampling and Attention—0
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization—0
CLAQ: Pushing the Limits of Low-Bit Post-Training Quantization for LLMsCode0
UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation—0
Di^2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimation—0
BeamVQ: Aligning Space-Time Forecasting Model via Self-training on Physics-aware Metrics—0
Node Identifiers: Compact, Discrete Representations for Efficient Graph LearningCode1
SpinQuant: LLM quantization with learned rotationsCode5
LoQT: Low-Rank Adapters for Quantized PretrainingCode2
M^3GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and GenerationCode1
PTQ4DiT: Post-training Quantization for Diffusion TransformersCode1
FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference—0
Massive MIMO-ISAC System With 1-Bit ADCs/DACs—0
Show:102550
← PrevPage 27 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