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 151–200 of 4925 papers

TitleStatusHype
Preventing Local Pitfalls in Vector Quantization via Optimal TransportCode2
Palu: Compressing KV-Cache with Low-Rank ProjectionCode2
PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-ResolutionCode2
Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor SearchCode2
On-Device Training Under 256KB MemoryCode2
NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural NetworksCode2
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language ModelsCode2
Optimizing Edge AI: A Comprehensive Survey on Data, Model, and System StrategiesCode2
ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular QuantizersCode2
MotionLLaMA: A Unified Framework for Motion Synthesis and ComprehensionCode2
D2GV: Deformable 2D Gaussian Splatting for Video Representation in 400FPSCode2
Neural Network Compression Framework for fast model inferenceCode2
OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution FittingCode2
QuIP: 2-Bit Quantization of Large Language Models With GuaranteesCode2
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationCode2
MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains MoreCode2
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationCode2
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge UnderstandingCode2
Low-Rank Quantization-Aware Training for LLMsCode2
MAexp: A Generic Platform for RL-based Multi-Agent ExplorationCode2
MAUVE Scores for Generative Models: Theory and PracticeCode2
LoQT: Low-Rank Adapters for Quantized PretrainingCode2
Compressing Volumetric Radiance Fields to 1 MBCode2
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor SearchCode2
LLM-FP4: 4-Bit Floating-Point Quantized TransformersCode2
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object DetectionCode2
Atom: Low-bit Quantization for Efficient and Accurate LLM ServingCode2
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPSCode2
Lossless Compression of Vector IDs for Approximate Nearest Neighbor SearchCode2
MobileQuant: Mobile-friendly Quantization for On-device Language ModelsCode2
LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language ModelsCode2
Compressing Large Language Models using Low Rank and Low Precision DecompositionCode2
Compact 3D Gaussian Representation for Radiance FieldCode2
A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image GenerationCode2
CompGS: Smaller and Faster Gaussian Splatting with Vector QuantizationCode2
Adapting Large Language Models by Integrating Collaborative Semantics for RecommendationCode2
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable ApproachesCode2
MBQ: Modality-Balanced Quantization for Large Vision-Language ModelsCode2
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised TrainingCode2
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block QuantizationCode2
LeanVec: Searching vectors faster by making them fitCode2
any4: Learned 4-bit Numeric Representation for LLMsCode2
AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-ResolutionCode2
Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMsCode2
INT-FlashAttention: Enabling Flash Attention for INT8 QuantizationCode2
I-ViT: Integer-only Quantization for Efficient Vision Transformer InferenceCode2
Imp: Highly Capable Large Multimodal Models for Mobile DevicesCode2
Model-Preserving Adaptive RoundingCode2
An Empirical Study of Qwen3 QuantizationCode2
HAQ: Hardware-Aware Automated Quantization with Mixed PrecisionCode2
Show:102550
← PrevPage 4 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