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 101–125 of 4925 papers

TitleStatusHype
MotionGPT: Human Motion as a Foreign LanguageCode3
MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsCode3
A Survey on Inference Optimization Techniques for Mixture of Experts ModelsCode3
A Survey on Large Language Model Acceleration based on KV Cache ManagementCode3
MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector QuantizationCode3
Data Generation for Hardware-Friendly Post-Training QuantizationCode3
CV-VAE: A Compatible Video VAE for Latent Generative Video ModelsCode3
Ditto: Quantization-aware Secure Inference of Transformers upon MPCCode3
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion ModelsCode3
TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style ControlCode3
Compact 3D Gaussian Splatting for Static and Dynamic Radiance FieldsCode3
Compact 3D Scene Representation via Self-Organizing Gaussian GridsCode3
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language ModelCode3
COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 TrainingCode3
8-bit Optimizers via Block-wise QuantizationCode3
DPLM-2: A Multimodal Diffusion Protein Language ModelCode3
LLM-QAT: Data-Free Quantization Aware Training for Large Language ModelsCode3
The Unreasonable Ineffectiveness of the Deeper LayersCode3
OneBit: Towards Extremely Low-bit Large Language ModelsCode3
RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust AdaptationCode3
APOLLO: SGD-like Memory, AdamW-level PerformanceCode3
TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and GenerationCode3
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV CacheCode3
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable ApproachesCode2
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block QuantizationCode2
Show:102550
← PrevPage 5 of 197Next →
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