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 1051–1100 of 4925 papers

TitleStatusHype
Private LoRA Fine-tuning of Open-Source LLMs with Homomorphic Encryption—0
Improving Block-Wise LLM Quantization by 4-bit Block-Wise Optimal Float (BOF4): Analysis and Variations—0
Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference—0
Turbo-ICL: In-Context Learning-Based Turbo Equalization—0
LightNobel: Improving Sequence Length Limitation in Protein Structure Prediction Model via Adaptive Activation Quantization—0
Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model—0
ReactDance: Progressive-Granular Representation for Long-Term Coherent Reactive Dance Generation—0
Low-bit Model Quantization for Deep Neural Networks: A SurveyCode0
LiteLMGuard: Seamless and Lightweight On-Device Prompt Filtering for Safeguarding Small Language Models against Quantization-induced Risks and VulnerabilitiesCode0
Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning—0
On-Device LLM for Context-Aware Wi-Fi RoamingCode0
3D Gaussian Splatting Data Compression with Mixture of Priors—0
Lightweight Clinical Decision Support System using QLoRA-Fine-Tuned LLMs and Retrieval-Augmented Generation—0
PROM: Prioritize Reduction of Multiplications Over Lower Bit-Widths for Efficient CNNs—0
Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques—0
RobSurv: Vector Quantization-Based Multi-Modal Learning for Robust Cancer Survival Prediction—0
Rapid yet accurate Tile-circuit and device modeling for Analog In-Memory Computing—0
Quantitative Analysis of Performance Drop in DeepSeek Model QuantizationCode0
End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruning—0
Radio: Rate-Distortion Optimization for Large Language Model Compression—0
EntroLLM: Entropy Encoded Weight Compression for Efficient Large Language Model Inference on Edge Devices—0
Bielik 11B v2 Technical Report—0
NeuroSim V1.5: Improved Software Backbone for Benchmarking Compute-in-Memory Accelerators with Device and Circuit-level Non-idealitiesCode0
Quantizing Diffusion Models from a Sampling-Aware Perspective—0
PASCAL: Precise and Efficient ANN- SNN Conversion using Spike Accumulation and Adaptive Layerwise Activation—0
Efficient Fine-Tuning of Quantized Models via Adaptive Rank and Bitwidth—0
LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deployment—0
Efficient Vision-based Vehicle Speed Estimation—0
Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free—0
Aggregating empirical evidence from data strategy studies: a case on model quantization—0
Optimizing Deep Neural Networks using Safety-Guided Self CompressionCode0
Generative QoE Modeling: A Lightweight Approach for Telecom Networks—0
Optimization of embeddings storage for RAG systems using quantization and dimensionality reduction techniques—0
Precision Where It Matters: A Novel Spike Aware Mixed-Precision Quantization Strategy for LLaMA-based Language Models—0
Clustering-Based Evolutionary Federated Multiobjective Optimization and Learning—0
APG-MOS: Auditory Perception Guided-MOS Predictor for Synthetic Speech—0
FineQ: Software-Hardware Co-Design for Low-Bit Fine-Grained Mixed-Precision Quantization of LLMs—0
TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate—0
Partition Map-Based Fast Block Partitioning for VVC Inter CodingCode0
Pushing the boundary on Natural Language Inference—0
On-Device Qwen2.5: Efficient LLM Inference with Model Compression and Hardware Acceleration—0
Fast Autoregressive Models for Continuous Latent Generation—0
Precision Neural Network Quantization via Learnable Adaptive Modules—0
Distributed Optimization with Efficient Communication, Event-Triggered Solution Enhancement, and Operation Stopping—0
TeLLMe: An Energy-Efficient Ternary LLM Accelerator for Prefilling and Decoding on Edge FPGAs—0
Hexcute: A Tile-based Programming Language with Automatic Layout and Task-Mapping Synthesis—0
A LoRA-Based Approach to Fine-Tuning LLMs for Educational Guidance in Resource-Constrained SettingsCode0
Compute-Optimal LLMs Provably Generalize Better With Scale—0
StableQuant: Layer Adaptive Post-Training Quantization for Speech Foundation Models—0
Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Space—0
Show:102550
← PrevPage 22 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