activity
20242026
most citedAPHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing 2026Show all

2 papers · 1 filter

cs.LG2026

BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design

Yifu Ding, Xianglong Liu, Shenghao Jin +2

Ultra low-bit quantization brings substantial efficiency for Transformer-based models, but the accuracy degradation and limited GPU support hinder its wide usage. In this paper, we…

cs.LG2026

Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference

Yifu Ding, Xinhao Zhang, Jinyang Guo

Transformer-based large language models (LLMs) have demonstrated remarkable performance across a wide range of real-world tasks, but their inference cost remains prohibitively high…