Yating Huang — accepted AI-conference papers

2025

PathoHR: Hierarchical Reasoning for Vision-Language Models in Pathology

Yating Huang, Ziyan Huang, Lintao Xiang, Qijun Yang, Hujun Yin

EMNLP 2025

Accurate analysis of pathological images is essential for automated tumor diagnosis but remains challenging due to high structural similarity and subtle morphological variations in tissue images. Current vision-language (VL) models often struggle to capture the complex reasoning required for interpr

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Your Scale Factors are My Weapon: Targeted Bit-Flip Attacks on Vision Transformers via Scale Factor Manipulation

Jialai Wang, Yuxiao Wu, Weiye Xu, Yating Huang, Chao Zhang, Zongpeng Li +2

CVPR 2025poster

Vision Transformers (ViTs) have experienced significant progress and are quantized for deployment in resource-constrained applications. Quantized models are vulnerable to targeted bit-flip attacks (BFAs). A targeted BFA prepares a trigger and a corresponding Trojan/backdoor, inserting the latter (wi…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗