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 1551–1600 of 4925 papers

TitleStatusHype
GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian SplattingCode3
Vector Quantization for Deep-Learning-Based CSI Feedback in Massive MIMO Systems—0
Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding—0
Chronos: Learning the Language of Time SeriesCode7
COMQ: A Backpropagation-Free Algorithm for Post-Training QuantizationCode1
What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation—0
FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization—0
QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning—0
FrameQuant: Flexible Low-Bit Quantization for TransformersCode1
Micro-Fracture Detection in Photovoltaic Cells with Hardware-Constrained Devices and Computer Vision—0
The Impact of Quantization on the Robustness of Transformer-based Text Classifiers—0
Enhancing Multimodal Unified Representations for Cross Modal Generalization—0
Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN InferenceCode0
GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLMCode2
Self-Adapting Large Visual-Language Models to Edge Devices across Visual ModalitiesCode1
QAQ: Quality Adaptive Quantization for LLM KV CacheCode2
On-demand Quantization for Green Federated Generative Diffusion in Mobile Edge Networks—0
LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression—0
ShortGPT: Layers in Large Language Models are More Redundant Than You ExpectCode2
Adaptive Integrate-and-Fire Time Encoding Machine with Quantization—0
Design of Stochastic Quantizers for Privacy Preservation—0
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs—0
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion ModelsCode3
Behavior Generation with Latent ActionsCode3
VQSynery: Robust Drug Synergy Prediction With Vector Quantization Mechanism—0
Deep-Learned Compression for Radio-Frequency Signal Classification—0
FlowPrecision: Advancing FPGA-Based Real-Time Fluid Flow Estimation with Linear Quantization—0
Towards efficient deep autoencoders for multivariate time series anomaly detection—0
Neural Network Assisted Lifting Steps For Improved Fully Scalable Lossy Image Compression in JPEG 2000Code0
Better Schedules for Low Precision Training of Deep Neural Networks—0
A Hierarchical Federated Learning Approach for the Internet of Things—0
On the Compressibility of Quantized Large Language Models—0
Extracting Usable Predictions from Quantized Networks through Uncertainty Quantification for OOD DetectionCode0
LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive QuantizationCode1
IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens IntactCode3
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel ApproachCode1
BasedAI: A decentralized P2P network for Zero Knowledge Large Language Models (ZK-LLMs)—0
NeuraLUT: Hiding Neural Network Density in Boolean Synthesizable FunctionsCode1
Variable-Rate Learned Image Compression with Multi-Objective Optimization and Quantization-Reconstruction Offsets—0
T3DNet: Compressing Point Cloud Models for Lightweight 3D Recognition—0
Ef-QuantFace: Streamlined Face Recognition with Small Data and Low-Bit Precision—0
No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization—0
FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization—0
Evaluating Quantized Large Language ModelsCode2
Inpainting Computational Fluid Dynamics with Deep Learning—0
Neural Video Compression with Feature Modulation—0
Adaptive quantization with mixed-precision based on low-cost proxy—0
Rethinking Mutual Information for Language Conditioned Skill Discovery on Imitation Learning—0
Distortion-Controlled Dithering with Reduced Recompression Rate—0
SPC-NeRF: Spatial Predictive Compression for Voxel Based Radiance Field—0
Show:102550
← PrevPage 32 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