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 301–350 of 4925 papers

TitleStatusHype
APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision TransformersCode1
GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric CalibrationCode2
HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement—0
Moment Quantization for Video Temporal Grounding—0
LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi—0
When Reasoning Meets Compression: Benchmarking Compressed Large Reasoning Models on Complex Reasoning Tasks—0
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and QuantizationCode1
QSViT: A Methodology for Quantizing Spiking Vision Transformers—0
SQuat: Subspace-orthogonal KV Cache Quantization—0
Model Hemorrhage and the Robustness Limits of Large Language Models—0
Style Quantization for Data-Efficient GAN Training—0
Cocktail: Chunk-Adaptive Mixed-Precision Quantization for Long-Context LLM Inference—0
NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations—0
MCRB for Parameter Estimation from One-Bit Quantized and Oversampled Measurements—0
Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space ModelsCode2
Make Some Noise: Towards LLM audio reasoning and generation using sound tokens—0
Long-Tail Crisis in Nearest Neighbor Language Models—0
A Refined Analysis of Massive Activations in LLMsCode1
Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration—0
Harmonizing Visual Representations for Unified Multimodal Understanding and GenerationCode2
HOT: Hadamard-based Optimized TrainingCode0
MoQa: Rethinking MoE Quantization with Multi-stage Data-model Distribution Awareness—0
VADMamba: Exploring State Space Models for Fast Video Anomaly DetectionCode1
A 71.2-μW Speech Recognition Accelerator with Recurrent Spiking Neural Network—0
MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation—0
QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation DecompositionCode0
SINR: Sparsity Driven Compressed Implicit Neural Representations—0
GENIUS: A Generative Framework for Universal Multimodal SearchCode2
LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy PreservationCode1
QSID-MPC: Model Predictive Control with System Identification from Quantized Data—0
FFN Fusion: Rethinking Sequential Computation in Large Language Models—0
GranQ: Granular Zero-Shot Quantization with Channel-Wise Activation Scaling in QAT—0
Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization—0
BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV CacheCode2
4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video—0
Energy-Aware LLMs: A step towards sustainable AI for downstream applications—0
Improving Quantization with Post-Training Model Expansion—0
Variance Control via Weight Rescaling in LLM Pre-trainingCode0
QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the EdgeCode1
Neural Networks: According to the Principles of Grassmann Algebra—0
Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models—0
Learning Linear Block Codes with Gradient Quantization—0
SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs—0
Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction—0
Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation—0
LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices—0
FP4DiT: Towards Effective Floating Point Quantization for Diffusion TransformersCode0
PARQ: Piecewise-Affine Regularized Quantization—0
RAG-based User Profiling for Precision Planning in Mixed-precision Over-the-Air Federated Learning—0
Natural Quantization of Neural NetworksCode0
Show:102550
← PrevPage 7 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