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 851–900 of 4925 papers

TitleStatusHype
Sliding DFT-based Signal Recovery for Modulo ADC with 1-bit Folding Information—0
A Counterexample in Cross-Correlation Template Matching—0
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor SearchCode2
The Nature of Mathematical Modeling and Probabilistic Optimization Engineering in Generative AI—0
Adaptive Wireless Image Semantic Transmission: Design, Simulation, and Prototype Validation—0
Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ?—0
Self-calibration for Language Model Quantization and Pruning—0
Pyramid Vector Quantization for LLMs—0
Catastrophic Failure of LLM Unlearning via QuantizationCode1
Continuous Speech Synthesis using per-token Latent Diffusion—0
Residual vector quantization for KV cache compression in large language modelCode1
Large Deviation Upper Bounds and Improved MSE Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry—0
Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces—0
LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec—0
SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training—0
Lossless KV Cache Compression to 2%—0
Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language BenchmarksCode0
SNAC: Multi-Scale Neural Audio CodecCode4
Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs—0
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary SearchCode1
Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching—0
Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees—0
DART: Disentanglement of Accent and Speaker Representation in Multispeaker Text-to-Speech—0
AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations—0
SimLayerKV: A Simple Framework for Layer-Level KV Cache ReductionCode2
Quamba: A Post-Training Quantization Recipe for Selective State Space ModelsCode2
Optimal Quantization for Matrix MultiplicationCode0
Progressive Mixed-Precision Decoding for Efficient LLM Inference—0
DPLM-2: A Multimodal Diffusion Protein Language ModelCode3
Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMsCode1
Learning Graph Quantized TokenizersCode1
A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models—0
ERVQ: Enhanced Residual Vector Quantization with Intra-and-Inter-Codebook Optimization for Neural Audio Codecs—0
Channel-Wise Mixed-Precision Quantization for Large Language Models—0
COMET: Towards Partical W4A4KV4 LLMs Serving—0
DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMsCode0
FairGLVQ: Fairness in Partition-Based ClassificationCode0
Scaling Laws for Post Training Quantized Large Language Models—0
Efficiera Residual Networks: Hardware-Friendly Fully Binary Weight with 2-bit Activation Model Achieves Practical ImageNet AccuracyCode0
Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural NetworksCode1
Latent Action Pretraining from VideosCode3
QSpec: Speculative Decoding with Complementary Quantization Schemes—0
Real-Time Stress Detection via Photoplethysmogram Signals: Implementation of a Combined Continuous Wavelet Transform and Convolutional Neural Network on Resource-Constrained Microcontrollers—0
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming HeadsCode4
SLaNC: Static LayerNorm Calibration—0
Gaussian Mixture Vector Quantization with Aggregated Categorical Posterior—0
When Attention Sink Emerges in Language Models: An Empirical ViewCode2
Gradient-Free Neural Network Training on the Edge—0
GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation—0
FlatQuant: Flatness Matters for LLM QuantizationCode3
Show:102550
← PrevPage 18 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