Zhenyu Yi

Zhenyu Yi

M.S. student @ Shanghai Jiao Tong University

Medical AI 路
Multimodal Learning 路
Efficient MLLMs

馃摑 Publications

First-author and co-first-author papers. Click any title for details, abstract, and BibTeX.

MICCAI 2026
Brain-Adapter: A Dual-Stream Vision-Language MIL Framework for Comprehensive 3D CT Diagnosis of Acute Intracranial Pathologies
Zhenyu Yi*, Zhiyun Song, Yusong Sun, Zelin Liu, Manman Fei, Zhenhao Li, Jiaxuan Zhao, Xu Han, Lichi Zhang
A dual-stream vision-language MIL framework for comprehensive 3D CT diagnosis of acute intracranial pathologies.
Brain-Adapter: A Dual-Stream Vision-Language MIL Framework for Comprehensive 3D CT Diagnosis of Acute Intracranial Pathologies
arXiv 路 2026 路 Preprint
CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding
Zhenyu Yi*, Qiang Hu, Zhenhao Li, Jiaxuan Zhao, Yusong Sun, Lichi Zhang
A training-free token allocation framework for efficient 3D medical volume understanding with cross-slice evidence reallocation.
CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding
MICCAI 2026
EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment
Zhenyu Yi*, Jianwei Xu*, Yue Hu, Zhongwei Qiu, Sijing Li, Liang Huang, Bin Lv, Ling Zhang, Yingda Xia
An endoscopy vision-language pre-training framework with anatomy-guided sparsity and progressive alignment.
EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment
Medical Image Analysis (MedIA) 路 2026
Learning from Limited Phenotype-Level Annotations for Promoting Multiple Instance Learning in Endoscopic Helicobacter pylori Infection Diagnosis
Zhenyu Yi*, Jianwei Xu*, Yue Hu*, Liang Huang, Zhilin Zheng, Haifeng Jin, Panpan Ma, Tanzhou Chen, Jie Pan, Xiaoyun Ding, Fangfang Zhang, Jiang Liu, Xiaoteng Wang, Yingda Xia, Bin Lv, Ling Zhang
A phenotype-aware MIL framework for endoscopic H. pylori infection diagnosis with limited fine-grained annotations.
Learning from Limited Phenotype-Level Annotations for Promoting Multiple Instance Learning in Endoscopic Helicobacter pylori Infection Diagnosis
MICCAI 2024 路 Oral (<3%)
SALI: Short-Term Alignment and Long-Term Interaction Network for Colonoscopy Video Polyp Segmentation
Qiang Hu*, Zhenyu Yi*, Ying Zhou, Fang Peng, Mei Liu, Qiang Li, Zhiwei Wang
A hybrid temporal interaction network for colonoscopy video polyp segmentation.
SALI: Short-Term Alignment and Long-Term Interaction Network for Colonoscopy Video Polyp Segmentation