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 1251–1300 of 4925 papers

TitleStatusHype
xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation MetricsCode0
SDQ: Sparse Decomposed Quantization for LLM Inference—0
High-Fidelity Facial Albedo Estimation via Texture Quantization—0
Q-SNNs: Quantized Spiking Neural Networks—0
Attention-aware Post-training Quantization without Backpropagation—0
Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates—0
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language ModelsCode1
MSE Minimization in RIS-Aided MU-MIMO with Discrete Phase Shifts and Fronthaul Quantization—0
Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization—0
ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint ShrinkingCode1
Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%Code2
QTIP: Quantization with Trellises and Incoherence ProcessingCode1
Autoregressive Image Generation without Vector QuantizationCode5
Deep-Learning-Based Channel Estimation for Distributed MIMO with 1-bit Radio-Over-Fiber Fronthaul—0
Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization—0
Promoting Data and Model Privacy in Federated Learning through Quantized LoRA—0
An Analysis on Quantizing Diffusion Transformers—0
Optimization of Armv9 architecture general large language model inference performance based on Llama.cppCode0
Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and ToolboxCode1
Memory Faults in Activation-sparse Quantized Deep Neural Networks: Analysis and Mitigation using Sharpness-aware Training—0
How Should We Extract Discrete Audio Tokens from Self-Supervised Models?—0
Optimizing Byte-level Representation for End-to-end ASR—0
One-pass Multiple Conformer and Foundation Speech Systems Compression and Quantization Using An All-in-one Neural Model—0
QQQ: Quality Quattuor-Bit Quantization for Large Language ModelsCode2
Precipitation Nowcasting Using Physics Informed Discriminator Generative Models—0
GEB-1.3B: Open Lightweight Large Language Model—0
Human-level molecular optimization driven by mol-gene evolution—0
ToneUnit: A Speech Discretization Approach for Tonal Language Speech Synthesis—0
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language ModelsCode2
Q-S5: Towards Quantized State Space ModelsCode0
MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction—0
OpenVLA: An Open-Source Vision-Language-Action ModelCode9
ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models—0
MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases—0
Compressive Beam Alignment for Indoor Millimeter-Wave Systems—0
Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization—0
VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment—0
Examining Post-Training Quantization for Mixture-of-Experts: A BenchmarkCode1
FoldToken2: Learning compact, invariant and generative protein structure language—0
Image and Video Tokenization with Binary Spherical QuantizationCode3
T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text—0
TernaryLLM: Ternarized Large Language Model—0
The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs—0
2DQuant: Low-bit Post-Training Quantization for Image Super-ResolutionCode1
Topological Analysis for Detecting Anomalies (TADA) in Time Series—0
Low-Rank Quantization-Aware Training for LLMsCode2
Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks—0
Efficient Neural Compression with Inference-time Decoding—0
Towards Lightweight Speaker Verification via Adaptive Neural Network Quantization—0
From Analog to Digital: Multi-Order Digital Joint Coding-Modulation for Semantic CommunicationCode1
Show:102550
← PrevPage 26 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