Yunshan Zhong

8

Papers

2

Total Citations

Papers (8)

AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model

Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers

Learning Image Demoireing from Unpaired Real Data

CaM: Cache Merging for Memory-efficient LLMs Inference

ERQ: Error Reduction for Post-Training Quantization of Vision Transformers

IntraQ: Learning Synthetic Images With Intra-Class Heterogeneity for Zero-Shot Network Quantization

Fine-Grained Data Distribution Alignment for Post-Training Quantization

Dynamic Dual Trainable Bounds for Ultra-Low Precision Super-Resolution Networks