papers

Publications (6)

cs.CV2026

MedARC: Training-Free Adaptive Redundancy Compression of Visual Tokens for 3D Medical Vision-Language Models

Yitao Zhu, Mengjun Liu, Yingji Fu +2

MedARC is a training-free method that compresses redundant visual tokens in 3D medical images for vision‑language models by scoring token importance with multiple cues and merging…

#3d medical imaging#vision-language models#token compression#adaptive redundancy
cs.GR2025

Brain Connectivity Network Structure Learning For Brain Disorder Diagnosis

Dongdong Chen, Linlin Yao, Mengjun Liu +7

Recent studies in neuroscience highlight the significant potential of brain connectivity networks, which are commonly constructed from functional magnetic resonance imaging (fMRI)…

eess.IV2023

Arbitrary Reduction of MRI Inter-slice Spacing Using Hierarchical Feature Conditional Diffusion

Xin Wang, Zhenrong Shen, Zhiyun Song +5

Magnetic resonance (MR) images collected in 2D scanning protocols typically have large inter-slice spacing, resulting in high in-plane resolution but reduced through-plane resoluti…

eess.IV2024

REHRSeg: Unleashing the Power of Self-Supervised Super-Resolution for Resource-Efficient 3D MRI Segmentation

Zhiyun Song, Yinjie Zhao, Xiaomin Li +9

High-resolution (HR) 3D magnetic resonance imaging (MRI) can provide detailed anatomical structural information, enabling precise segmentation of regions of interest for various me…

eess.IV2023

Spatial Attention-based Implicit Neural Representation for Arbitrary Reduction of MRI Slice Spacing

Xin Wang, Sheng Wang, Honglin Xiong +7

Magnetic resonance (MR) images collected in 2D clinical protocols typically have large inter-slice spacing, resulting in high in-plane resolution and reduced through-plane resoluti…

cs.CR2022

Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Survey

Hui Cao, Wenlong Zou, Yinkun Wang +2

Since the 2004 DARPA Grand Challenge, the autonomous driving technology has witnessed nearly two decades of rapid development. Particularly, in recent years, with the application o…