Zhongcheng Li — accepted AI-conference papers

2026

QuEPT: Quantized Elastic Precision Transformers with One-Shot Calibration for Multi-Bit Switching

Ke Xu, Yixin Wang, Zhongcheng Li, Hao Cui, Jinshui Hu, Xingyi Zhang

AAAI 2026technical

Elastic precision quantization enables multi-bit deployment via a single optimization pass, fitting diverse quantization scenarios. Yet, the high storage and optimization costs associated with the Transformer architecture, research on elastic quantization remains limited, particularly for large lang

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

PTMQ: Post-training Multi-Bit Quantization of Neural Networks

Ke Xu, Zhongcheng Li, Shanshan Wang, Xingyi Zhang

AAAI 2024technical

The ability of model quantization with arbitrary bit-width to dynamically meet diverse bit-width requirements during runtime has attracted significant attention. Recent research has focused on optimizing large-scale training methods to achieve robust bit-width adaptation, which is a time-consuming p…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗