SOTAVerified

Data Free Quantization

Data Free Quantization is a technique to achieve a highly accurate quantized model without accessing any training data.

Source: Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 37 papers

TitleStatusHype
Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning—0
Data-Free Quantization via Pseudo-label Filtering—0
Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization—0
Diversifying Sample Generation for Accurate Data-Free Quantization—0
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs—0
Enhancing Diversity for Data-free Quantization—0
Generative Zero-shot Network Quantization—0
MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity—0
OuroMamba: A Data-Free Quantization Framework for Vision Mamba Models—0
Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare—0
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.