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 251–300 of 4925 papers

TitleStatusHype
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object DetectionCode2
HAQ: Hardware-Aware Automated Quantization with Mixed PrecisionCode2
Harmonizing Visual Representations for Unified Multimodal Understanding and GenerationCode2
GuidedQuant: Large Language Model Quantization via Exploiting End Loss GuidanceCode2
A Closer Look at Hardware-Friendly Weight QuantizationCode2
GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric CalibrationCode2
An Empirical Study of Qwen3 QuantizationCode2
AiSAQ: All-in-Storage ANNS with Product Quantization for DRAM-free Information RetrievalCode2
GENIUS: A Generative Framework for Universal Multimodal SearchCode2
GaussianToken: An Effective Image Tokenizer with 2D Gaussian SplattingCode2
GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLMCode2
GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook RetrievalCode2
BitVLA: 1-bit Vision-Language-Action Models for Robotics ManipulationCode2
From Tiny Machine Learning to Tiny Deep Learning: A SurveyCode2
AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory ComputingCode2
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPSCode2
On-Device Training Under 256KB MemoryCode2
RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor SearchCode2
Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMsCode2
any4: Learned 4-bit Numeric Representation for LLMsCode2
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Confounding Tradeoffs for Neural Network QuantizationCode1
Fine-tuning Quantized Neural Networks with Zeroth-order OptimizationCode1
4-bit Shampoo for Memory-Efficient Network TrainingCode1
A Greedy Algorithm for Quantizing Neural NetworksCode1
Conditional Coding and Variable Bitrate for Practical Learned Video CodingCode1
Finite Scalar Quantization: VQ-VAE Made SimpleCode1
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
COMQ: A Backpropagation-Free Algorithm for Post-Training QuantizationCode1
Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement LearningCode1
Compression with Bayesian Implicit Neural RepresentationsCode1
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
Fine-grained Data Distribution Alignment for Post-Training QuantizationCode1
Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded PlatformsCode1
Few shot font generation via transferring similarity guided global style and quantization local styleCode1
FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated LearningCode1
Compressing LLMs: The Truth is Rarely Pure and Never SimpleCode1
Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint ReductionCode1
FFNeRV: Flow-Guided Frame-Wise Neural Representations for VideosCode1
Compress Any Segment Anything Model (SAM)Code1
AFPQ: Asymmetric Floating Point Quantization for LLMsCode1
Feature Quantization Improves GAN TrainingCode1
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal HashingCode1
Context-aware Communication for Multi-agent Reinforcement LearningCode1
Federated Optimization Algorithms with Random Reshuffling and Gradient CompressionCode1
FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix ApproximationCode1
FastText.zip: Compressing text classification modelsCode1
AffineQuant: Affine Transformation Quantization for Large Language ModelsCode1
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
Compact representations of convolutional neural networks via weight pruning and quantizationCode1
Show:102550
← PrevPage 6 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