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 451–500 of 4925 papers

TitleStatusHype
Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative AnalysisCode0
Rotate, Clip, and Partition: Towards W2A4KV4 Quantization by Integrating Rotation and Learnable Non-uniform Quantizer—0
Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer GateCode0
Towards Reasoning Ability of Small Language Models—0
Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?—0
On the Logic Elements Associated with Round-Off Errors and Gaussian Blur in Image Registration: A Simple Case of Commingling—0
Towards Efficient Pre-training: Exploring FP4 Precision in Large Language Models—0
On Quantizing Neural Representation for Variable-Rate Video CodingCode0
Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit ViewCode0
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMsCode1
Weighted quantization using MMD: From mean field to mean shift via gradient flowsCode0
Towards Watermarking of Open-Source LLMs—0
Low-Complexity On-Grid Channel Estimation for Partially-Connected Hybrid XL-MIMO—0
CISSIR: Beam Codebooks with Self-Interference Reduction Guarantees for Integrated Sensing and Communication Beyond 5GCode1
EmbBERT-Q: Breaking Memory Barriers in Embedded NLPCode0
NestQuant: Nested Lattice Quantization for Matrix Products and LLMs—0
RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models—0
SQ-GAN: Semantic Image Communications Using Masked Vector QuantizationCode1
Exploiting Non-uniform Quantization for Enhanced ILC in Wideband Digital Pre-distortion—0
Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding—0
Contextual Compression Encoding for Large Language Models: A Novel Framework for Multi-Layered Parameter Space Pruning—0
Scalable Thermodynamic Second-order Optimization—0
LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits—0
Loss Landscape Analysis for Reliable Quantized ML Models for Scientific SensingCode0
Vision-Language Models for Edge Networks: A Comprehensive Survey—0
Column-wise Quantization of Weights and Partial Sums for Accurate and Efficient Compute-In-Memory AcceleratorsCode0
MEMHD: Memory-Efficient Multi-Centroid Hyperdimensional Computing for Fully-Utilized In-Memory Computing Architectures—0
HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates—0
Conditional Distribution Quantization in Machine Learning—0
Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation—0
Matryoshka Quantization—0
Demystifying Singular Defects in Large Language Models—0
GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing UnitsCode0
Gradient Based Method for the Fusion of Lattice Quantizers—0
Physics-Conditioned Diffusion Models for Lattice Gauge TheoryCode0
IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech SystemCode11
QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation—0
AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers—0
Scalable and consistent embedding of probability measures into Hilbert spaces via measure quantization—0
Efficient Evaluation of Quantization-Effects in Neural Codecs—0
QuEST: Stable Training of LLMs with 1-Bit Weights and ActivationsCode2
A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications—0
Exploring Model Invariance with Discrete Search for Ultra-Low-Bit Quantization—0
KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM InferenceCode0
TQ-DiT: Efficient Time-Aware Quantization for Diffusion Transformers—0
Asymptotic Analysis of One-bit Quantized Box-Constrained Precoding in Large-Scale Multi-User Systems—0
SensorChat: Answering Qualitative and Quantitative Questions during Long-Term Multimodal Sensor Interactions—0
HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference—0
ParetoQ: Scaling Laws in Extremely Low-bit LLM QuantizationCode3
Unlocking Efficient Large Inference Models: One-Bit Unrolling Tips the Scales—0
Show:102550
← PrevPage 10 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