CB

Chengzhu Bao

0009-0008-1799-8010

cs.LGcs.AI

On Valency

published · living versions

W_abjnt43j·v1 · currentpublished

ProQuant: Preserving Expert Quality over Quantity in Ultra-Low-Bit Quantization of Mixture-of-Experts Models

with Jiaqi Chen, Xianglong Yan, Xie Chen, Yulun Zhang

1 version

Preprints & journals

3 papers in the corpus · 2026

RATIO: Reasoning Analysis and Token-level Inference Optimization for Quantized Reasoning Models2609.39801v1 · Chengzhu Bao, Xianglong Yan, Tianao Zhang et al.2026 · 0 citationsarXiv

FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling2608.01847v1 · Xianglong Yan, Hong Liu, Chengzhu Bao et al.2026 · 0 citationsarXiv

SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization2605.12245v1 · Chengzhu Bao, Xianglong Yan, Zhiteng Li et al.2026 · 0 citationsarXiv

Career total: 5 works. 3 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.