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 1001–1050 of 4925 papers

TitleStatusHype
NeUQI: Near-Optimal Uniform Quantization Parameter InitializationCode0
NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache—0
Task Specific Pruning with LLM-Sieve: How Many Parameters Does Your Task Really Need?—0
Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM—0
Beyond Discreteness: Finite-Sample Analysis of Straight-Through Estimator for Quantization—0
NQKV: A KV Cache Quantization Scheme Based on Normal Distribution Characteristics—0
DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP ProtectionCode0
FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-designCode0
Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing—0
Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information—0
Harnessing Large Language Models Locally: Empirical Results and Implications for AI PCCode0
InTreeger: An End-to-End Framework for Integer-Only Decision Tree Inference—0
Is (Selective) Round-To-Nearest Quantization All You Need?—0
Rate-Distortion Optimization with Non-Reference Metrics for UGC Compression—0
EfficientLLM: Efficiency in Large Language Models—0
Layer-wise Quantization for Quantized Optimistic Dual Averaging—0
Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference—0
Through a Compressed Lens: Investigating the Impact of Quantization on LLM Explainability and Interpretability—0
Deep Unfolding with Kernel-based Quantization in MIMO Detection—0
QUADS: QUAntized Distillation Framework for Efficient Speech Language UnderstandingCode0
An Overview of Arithmetic Adaptations for Inference of Convolutional Neural Networks on Re-configurable HardwareCode0
UniHM: Universal Human Motion Generation with Object Interactions in Indoor Scenes—0
GANCompress: GAN-Enhanced Neural Image Compression with Binary Spherical Quantization—0
A3 : an Analytical Low-Rank Approximation Framework for Attention—0
Automatic mixed precision for optimizing gained time with constrained loss mean-squared-error based on model partition to sequential sub-graphs—0
KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache—0
Hyperbolic Residual Quantization: Discrete Representations for Data with Latent Hierarchies—0
CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design—0
PMQ-VE: Progressive Multi-Frame Quantization for Video EnhancementCode0
FedHQ: Hybrid Runtime Quantization for Federated Learning—0
QVGen: Pushing the Limit of Quantized Video Generative Models—0
MARRS: Masked Autoregressive Unit-based Reaction Synthesis—0
Gaussian Weight Sampling for Scalable, Efficient and Stable Pseudo-Quantization Training—0
Benchmarking CFAR and CNN-based Peak Detection Algorithms in ISAC under Hardware Impairments—0
Addition is almost all you need: Compressing neural networks with double binary factorizationCode0
Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization—0
Formal Uncertainty Propagation for Stochastic Dynamical Systems with Additive Noise—0
VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits—0
TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain AdaptationCode0
A probabilistic framework for dynamic quantization—0
Efficient Mixed Precision Quantization in Graph Neural NetworksCode0
Zero-shot Quantization: A Comprehensive Survey—0
Multi-Layer Hierarchical Federated Learning with Quantization—0
Resource-Efficient Language Models: Quantization for Fast and Accessible Inference—0
Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption—0
Semantic Retention and Extreme Compression in LLMs: Can We Have Both?—0
Cognitive Non-Coherent Jamming Techniques for Frequency Selective Attacks—0
Efficient ANN-SNN Conversion with Error Compensation Learning—0
QuantX: A Framework for Hardware-Aware Quantization of Generative AI Workloads—0
An Extra RMSNorm is All You Need for Fine Tuning to 1.58 Bits—0
Show:102550
← PrevPage 21 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