collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models

Shengyuan Liu, Zanting Ye, Yunrui Lin +6

While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remai…

cs.CV2026

InViC: Intent-aware Visual Cues for Medical Visual Question Answering

Zhisong Wang, Ziyang Chen, Zanting Ye +3

Medical visual question answering (Med-VQA) aims to answer clinically relevant questions grounded in medical images. However, existing multimodal large language models (MLLMs) ofte…

cs.CV2026

Unveiling and Bridging the Functional Perception Gap in MLLMs: Atomic Visual Alignment and Hierarchical Evaluation via PET-Bench

Zanting Ye, Xiaolong Niu, Xuanbin Wu +14

While Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in tasks such as abnormality detection and report generation for anatomical modalities, thei…

cs.CV2025

OralGPT-Omni: A Versatile Dental Multimodal Large Language Model

Jing Hao, Yuci Liang, Lizhuo Lin +12

Multimodal Large Language Models (MLLMs) have exhibited immense potential across numerous medical specialties; yet, dentistry remains underexplored, in part due to limited domain-s…

cs.CV2025

FSDA-DG: Improving Cross-Domain Generalizability of Medical Image Segmentation with Few Source Domain Annotations

Zanting Ye, Ke Wang, Wenbing Lv +2

Deep learning-based medical image segmentation faces significant challenges arising from limited labeled data and domain shifts. While prior approaches have primarily addressed the…

cs.CV2025

Semi-KAN: KAN Provides an Effective Representation for Semi-Supervised Learning in Medical Image Segmentation

Zanting Ye, Xiaolong Niu, Xuanbin Wu +3

Deep learning-based medical image segmentation has shown remarkable success; however, it typically requires extensive pixel-level annotations, which are both expensive and time-int…