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 1601–1650 of 4925 papers

TitleStatusHype
A Comprehensive Evaluation of Quantization Strategies for Large Language ModelsCode0
Data-freeWeight Compress and Denoise for Large Language Models—0
Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean SpeechCode2
LLM Inference Unveiled: Survey and Roofline Model InsightsCode4
EncodingNet: A Novel Encoding-based MAC Design for Efficient Neural Network AccelerationCode0
Towards Accurate Post-training Quantization for Reparameterized ModelsCode0
GPTVQ: The Blessing of Dimensionality for LLM Quantization—0
On the Arrow of Inference—0
Text me the data: Generating Ground Pressure Sequence from Textual Descriptions for HAR—0
APTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models—0
Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and DistillationCode1
FinGPT-HPC: Efficient Pretraining and Finetuning Large Language Models for Financial Applications with High-Performance Computing—0
In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training—0
Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval SystemsCode1
Tiny Reinforcement Learning for Quadruped Locomotion using Decision TransformersCode0
Language-Codec: Bridging Discrete Codec Representations and Speech Language ModelsCode3
Towards a tailored mixed-precision sub-8-bit quantization scheme for Gated Recurrent Units using Genetic Algorithms—0
WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More—0
Is It a Free Lunch for Removing Outliers during Pretraining?—0
DB-LLM: Accurate Dual-Binarization for Efficient LLMs—0
LaCo: Large Language Model Pruning via Layer CollapseCode1
Hierarchical Prior-based Super Resolution for Point Cloud Geometry CompressionCode1
OneBit: Towards Extremely Low-bit Large Language ModelsCode3
One-Bit Quantization and Sparsification for Multiclass Linear Classification with Strong Regularization—0
QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning—0
Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMsCode2
EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the EdgeCode1
BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-DistillationCode4
PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in ControlCode1
BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical DomainsCode2
Multi-Excitation Projective Simulation with a Many-Body Physics Inspired Inductive BiasCode0
Model Compression and Efficient Inference for Large Language Models: A Survey—0
QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inferenceCode2
Quantized Embedding Vectors for Controllable Diffusion Language Models—0
Lightweight Deep Learning Based Channel Estimation for Extremely Large-Scale Massive MIMO SystemsCode0
Rate-Splitting Multiple Access for Quantized ISAC LEO Satellite Systems: A Max-Min Fair Energy-Efficient Beam Design—0
Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers—0
BdSLW60: A Word-Level Bangla Sign Language DatasetCode0
TeMPO: Efficient Time-Multiplexed Dynamic Photonic Tensor Core for Edge AI with Compact Slow-Light Electro-Optic Modulator—0
Outlier-Aware Training for Low-Bit Quantization of Structural Re-Parameterized Networks—0
On Leaky-Integrate-and Fire as Spike-Train-Quantization Operator on Dirac-Superimposed Continuous-Time Signals—0
A Thorough Examination of Decoding Methods in the Era of LLMsCode1
LiRank: Industrial Large Scale Ranking Models at LinkedIn—0
RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization—0
Inducing Systematicity in Transformers by Attending to Structurally Quantized EmbeddingsCode1
Accurate LoRA-Finetuning Quantization of LLMs via Information RetentionCode2
RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization—0
Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecasting—0
ApiQ: Finetuning of 2-Bit Quantized Large Language ModelCode1
Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training—0
Show:102550
← PrevPage 33 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