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 201–250 of 4925 papers

TitleStatusHype
BitNet: Scaling 1-bit Transformers for Large Language ModelsCode2
Adapting Large Language Models by Integrating Collaborative Semantics for RecommendationCode2
PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models QuantizationCode2
Preventing Local Pitfalls in Vector Quantization via Optimal TransportCode2
BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical DomainsCode2
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object DetectionCode2
Binary Neural Networks: A SurveyCode2
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPSCode2
LLM-FP4: 4-Bit Floating-Point Quantized TransformersCode2
Binarized Neural Machine TranslationCode2
AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-ResolutionCode2
LeanVec: Searching vectors faster by making them fitCode2
D2GV: Deformable 2D Gaussian Splatting for Video Representation in 400FPSCode2
Quamba: A Post-Training Quantization Recipe for Selective State Space ModelsCode2
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable ApproachesCode2
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block QuantizationCode2
Dataset QuantizationCode2
DETRPose: Real-time end-to-end transformer model for multi-person pose estimationCode2
Imp: Highly Capable Large Multimodal Models for Mobile DevicesCode2
QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inferenceCode2
I-BERT: Integer-only BERT QuantizationCode2
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language ModelsCode2
An empirical study of LLaMA3 quantization: from LLMs to MLLMsCode2
BHViT: Binarized Hybrid Vision TransformerCode2
INT-FlashAttention: Enabling Flash Attention for INT8 QuantizationCode2
Harmonizing Visual Representations for Unified Multimodal Understanding and GenerationCode2
Atom: Low-bit Quantization for Efficient and Accurate LLM ServingCode2
HAQ: Hardware-Aware Automated Quantization with Mixed PrecisionCode2
GuidedQuant: Large Language Model Quantization via Exploiting End Loss GuidanceCode2
Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%Code2
A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image GenerationCode2
hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning DevicesCode2
Similarity search in the blink of an eye with compressed indicesCode2
SimLayerKV: A Simple Framework for Layer-Level KV Cache ReductionCode2
I-ViT: Integer-only Quantization for Efficient Vision Transformer InferenceCode2
GENIUS: A Generative Framework for Universal Multimodal SearchCode2
GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLMCode2
Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at ScaleCode2
GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook RetrievalCode2
From Tiny Machine Learning to Tiny Deep Learning: A SurveyCode2
GaussianToken: An Effective Image Tokenizer with 2D Gaussian SplattingCode2
FlowSE: Efficient and High-Quality Speech Enhancement via Flow MatchingCode2
any4: Learned 4-bit Numeric Representation for LLMsCode2
Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMsCode2
Accurate LoRA-Finetuning Quantization of LLMs via Information RetentionCode2
Efficient LLM Inference on CPUsCode2
An Empirical Study of Qwen3 QuantizationCode2
SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor SearchCode2
Efficient Video Face Enhancement with Enhanced Spatial-Temporal ConsistencyCode2
FBGEMM: Enabling High-Performance Low-Precision Deep Learning InferenceCode2
Show:102550
← PrevPage 5 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