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 751–800 of 4925 papers

TitleStatusHype
SoftmAP: Software-Hardware Co-design for Integer-Only Softmax on Associative Processors—0
MotionLLaMA: A Unified Framework for Motion Synthesis and ComprehensionCode2
LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and QuantizationCode0
Curvature in the Looking-Glass: Optimal Methods to Exploit Curvature of Expectation in the Loss Landscape—0
Rethinking Diffusion for Text-Driven Human Motion Generation—0
Lion Cub: Minimizing Communication Overhead in Distributed Lion—0
Downlink MIMO Channel Estimation from Bits: Recoverability and Algorithm—0
Beyond Task Vectors: Selective Task Arithmetic Based on Importance Metrics—0
Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression—0
Factorized Visual Tokenization and Generation—0
MixPE: Quantization and Hardware Co-design for Efficient LLM Inference—0
SKQVC: One-Shot Voice Conversion by K-Means Quantization with Self-Supervised Speech Representations—0
Representation Collapsing Problems in Vector Quantization—0
Efficient Video Face Enhancement with Enhanced Spatial-Temporal ConsistencyCode2
Efficient Online Inference of Vision Transformers by Training-Free TokenizationCode0
freePruner: A Training-free Approach for Large Multimodal Model Acceleration—0
FLARE: FP-Less PTQ and Low-ENOB ADC Based AMS-PiM for Error-Resilient, Fast, and Efficient Transformer Acceleration—0
TaQ-DiT: Time-aware Quantization for Diffusion Transformers—0
Quantization without TearsCode1
AutoMixQ: Self-Adjusting Quantization for High Performance Memory-Efficient Fine-Tuning—0
Quantized symbolic time series approximationCode2
Disco Intelligent Omni-Surfaces: 360-degree Fully-Passive Jamming Attacks—0
RTSR: A Real-Time Super-Resolution Model for AV1 Compressed Content—0
High-Throughput Blind Co-Channel Interference Cancellation for Edge Devices Using Depthwise Separable Convolutions, Quantization, and Pruning—0
SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor SearchCode2
Diffusion Product Quantization—0
BitMoD: Bit-serial Mixture-of-Datatype LLM AccelerationCode0
Towards Accurate and Efficient Sub-8-Bit Integer Training—0
EfQAT: An Efficient Framework for Quantization-Aware Training—0
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 QuantizationCode7
BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices—0
An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2Code0
Systolic Arrays and Structured Pruning Co-design for Efficient Transformers in Edge Systems—0
AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference—0
Communication Compression for Tensor Parallel LLM Inference—0
ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization—0
Towards Low-bit Communication for Tensor Parallel LLM Inference—0
Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning—0
HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment—0
Sketched Adaptive Federated Deep Learning: A Sharp Convergence Analysis—0
The Super Weight in Large Language ModelsCode2
HAFLQ: Heterogeneous Adaptive Federated LoRA Fine-tuned LLM with Quantization—0
Optimizing Large Language Models through Quantization: A Comparative Analysis of PTQ and QAT Techniques—0
Intelligent Fault Diagnosis of Type and Severity in Low-Frequency, Low Bit-Depth Signals—0
An asymmetric heuristic for trained ternary quantization based on the statistics of the weights: an application to medical signal classificationCode0
Expansion Quantization Network: An Efficient Micro-emotion Annotation and Detection FrameworkCode0
When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization—0
Rate-aware Compression for NeRF-based Volumetric Video—0
Qwen2.5-32B: Leveraging Self-Consistent Tool-Integrated Reasoning for Bengali Mathematical Olympiad Problem Solving—0
Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models—0
Show:102550
← PrevPage 16 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