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 251–275 of 4925 papers

TitleStatusHype
GuidedQuant: Large Language Model Quantization via Exploiting End Loss GuidanceCode2
HAQ: Hardware-Aware Automated Quantization with Mixed PrecisionCode2
GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook RetrievalCode2
A Closer Look at Hardware-Friendly Weight QuantizationCode2
GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLMCode2
Harmonizing Visual Representations for Unified Multimodal Understanding and GenerationCode2
AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory ComputingCode2
AiSAQ: All-in-Storage ANNS with Product Quantization for DRAM-free Information RetrievalCode2
Compressing Volumetric Radiance Fields to 1 MBCode2
From Tiny Machine Learning to Tiny Deep Learning: A SurveyCode2
FlowSE: Efficient and High-Quality Speech Enhancement via Flow MatchingCode2
Compressing Large Language Models using Low Rank and Low Precision DecompositionCode2
FBGEMM: Enabling High-Performance Low-Precision Deep Learning InferenceCode2
GaussianToken: An Effective Image Tokenizer with 2D Gaussian SplattingCode2
An Empirical Study of Qwen3 QuantizationCode2
GENIUS: A Generative Framework for Universal Multimodal SearchCode2
INT-FlashAttention: Enabling Flash Attention for INT8 QuantizationCode2
GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric CalibrationCode2
MAexp: A Generic Platform for RL-based Multi-Agent ExplorationCode2
Qinco2: Vector Compression and Search with Improved Implicit Neural CodebooksCode2
Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile DevicesCode1
F8Net: Fixed-Point 8-bit Only Multiplication for Network QuantizationCode1
4-bit Shampoo for Memory-Efficient Network TrainingCode1
A Greedy Algorithm for Quantizing Neural NetworksCode1
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal HashingCode1
Show:102550
← PrevPage 11 of 197Next →
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