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 1451–1500 of 4925 papers

TitleStatusHype
Privacy-Preserving UCB Decision Process Verification via zk-SNARKs—0
LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory—0
Variational quantization for state space modelsCode0
QGen: On the Ability to Generalize in Quantization Aware Training—0
Neural Network Approach for Non-Markovian Dissipative Dynamics of Many-Body Open Quantum Systems—0
Comprehensive Survey of Model Compression and Speed up for Vision Transformers—0
Tripod: Three Complementary Inductive Biases for Disentangled Representation LearningCode1
SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural NetworksCode5
Quantization of Large Language Models with an Overdetermined Basis—0
Efficient and accurate neural field reconstruction using resistive memory—0
TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models—0
SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous AgentsCode0
Bullion: A Column Store for Machine Learning—0
Lossy Image Compression with Foundation Diffusion Models—0
Full-Duplex Beyond Self-Interference: The Unlimited Sensing Way—0
Edge-Efficient Deep Learning Models for Automatic Modulation Classification: A Performance Analysis—0
1-bit Quantized On-chip Hybrid Diffraction Neural Network Enabled by Authentic All-optical Fully-connected Architecture—0
Frame Quantization of Neural Networks—0
Differentiable Search for Finding Optimal Quantization Strategy—0
CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent LayersCode0
Adapting LLaMA Decoder to Vision TransformerCode1
End-to-End Rate-Distortion Optimized 3D Gaussian RepresentationCode1
Encoder-Quantization-Motion-based Video Quality Metrics—0
AiSAQ: All-in-Storage ANNS with Product Quantization for DRAM-free Information RetrievalCode2
Collaborative Edge AI Inference over Cloud-RAN—0
Exploring Quantization and Mapping Synergy in Hardware-Aware Deep Neural Network AcceleratorsCode0
Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model MergingCode1
BinaryDM: Accurate Weight Binarization for Efficient Diffusion ModelsCode1
Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws—0
Investigating the Impact of Quantization on Adversarial Robustness—0
David and Goliath: An Empirical Evaluation of Attacks and Defenses for QNNs at the Deep EdgeCode0
Nanometer Scanning with Micrometer Sensing: Beating Quantization Constraints in Lissajous Trajectory Tracking—0
Gull: A Generative Multifunctional Audio Codec—0
Weakly Supervised Deep Hyperspherical Quantization for Image RetrievalCode0
What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data Pretrained Language Models—0
Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes—0
Outlier-Efficient Hopfield Layers for Large Transformer-Based ModelsCode1
Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation RegularizationCode0
TinyVQA: Compact Multimodal Deep Neural Network for Visual Question Answering on Resource-Constrained Devices—0
AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-ResolutionCode2
DI-Retinex: Digital-Imaging Retinex Theory for Low-Light Image Enhancement—0
CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech—0
Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models—0
Efficient Multi-Vector Dense Retrieval Using Bit VectorsCode2
DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization—0
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language ModelsCode3
NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation—0
On the Effect of Quantization on Dynamic Mode Decomposition—0
RefQSR: Reference-based Quantization for Image Super-Resolution Networks—0
Minimize Quantization Output Error with Bias CompensationCode0
Show:102550
← PrevPage 30 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