collaborators

6 papers

cs.CV2026

CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding

Zhenyu Yi, Qiang Hu, Zhenhao Li +3

Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices. However, this slice-wise formulation produces thousands of visual tokens that bu…

cs.CV2026

EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment

Zhenyu Yi, Jianwei Xu, Yue Hu +6

The development of foundation models (FMs) is crucial for advancing endoscopic image analysis. However, existing endoscopy FMs mainly rely on self-supervised learning from uni-moda…

eess.IV2026

E-MRL: Cross-view Aligned Evidence-driven Multimodal Reinforcement Learning for Reliable 3D Tumor Analysis

Sijing Li, Zhongwei Qiu, Zhuoya Wang +6

While Vision-Language Models (VLMs) show great promise in volumetric medical report generation, they frequently suffer from visual hallucinations and a lack of grounding in 3D CT d…

cs.CV2026

Brain-Adapter: A Dual-Stream Vision-Language MIL Framework for Comprehensive 3D CT Diagnosis of Acute Intracranial Pathologies

Zhenyu Yi, Zhiyun Song, Yusong Sun +6

Automated diagnosis of 3D brain CT scans is essential for critical care, yet it remains challenging due to the heavy reliance on manual annotations and the limited semantic underst…

cs.CV2024

MonoBox: Tightness-free Box-supervised Polyp Segmentation using Monotonicity Constraint

Qiang Hu, Zhenyu Yi, Ying Zhou +4

We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption. In cont…

cs.CV2024

SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation

Qiang Hu, Zhenyu Yi, Ying Zhou +4

Colonoscopy videos provide richer information in polyp segmentation for rectal cancer diagnosis. However, the endoscope's fast moving and close-up observing make the current method…