71 citations · 142 across the 12 of their papers we have counts for
12 papers
MedARC: Training-Free Adaptive Redundancy Compression of Visual Tokens for 3D Medical Vision-Language Models
Yitao Zhu, Mengjun Liu, Yingji Fu +2
Integrating 3D medical images with vision-language models (VLMs) holds substantial promise for computer-aided diagnosis. However, volumetric images generate prohibitively long visu…
IHF-Harmony: Multi-Modality Magnetic Resonance Images Harmonization using Invertible Hierarchy Flow Model
Pengli Zhu, Yitao Zhu, Haowen Pang +1
Retrospective MRI harmonization is limited by poor scalability across modalities and reliance on traveling subject datasets. To address these challenges, we introduce IHF-Harmony,…
VisionCAD: An Integration-Free Radiology Copilot Framework
Jiaming Li, Junlei Wu, Sheng Wang +7
Widespread clinical deployment of computer-aided diagnosis (CAD) systems is hindered by the challenge of integrating with existing hospital IT infrastructure. Here, we introduce Vi…
ReactDiff: Latent Diffusion for Facial Reaction Generation
Jiaming Li, Sheng Wang, Xin Wang +4
Given the audio-visual clip of the speaker, facial reaction generation aims to predict the listener's facial reactions. The challenge lies in capturing the relevance between video…
UniCAD: Efficient and Extendable Architecture for Multi-Task Computer-Aided Diagnosis System
Yitao Zhu, Yuan Yin, Zhenrong Shen +5
The growing complexity and scale of visual model pre-training have made developing and deploying multi-task computer-aided diagnosis (CAD) systems increasingly challenging and reso…
Med-LEGO: Editing and Adapting toward Generalist Medical Image Diagnosis
Yitao Zhu, Yuan Yin, Jiaming Li +5
The adoption of visual foundation models has become a common practice in computer-aided diagnosis (CAD). While these foundation models provide a viable solution for creating genera…
MITracker: Multi-View Integration for Visual Object Tracking
Mengjie Xu, Yitao Zhu, Haotian Jiang +8
Multi-view object tracking (MVOT) offers promising solutions to challenges such as occlusion and target loss, which are common in traditional single-view tracking. However, progres…
Inter-slice Super-resolution of Magnetic Resonance Images by Pre-training and Self-supervised Fine-tuning
Xin Wang, Zhiyun Song, Yitao Zhu +4
In clinical practice, 2D magnetic resonance (MR) sequences are widely adopted. While individual 2D slices can be stacked to form a 3D volume, the relatively large slice spacing can…
MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction
Yitao Zhu, Sheng Wang, Mengjie Xu +5
Multiple cameras can provide comprehensive multi-view video coverage of a person. Fusing this multi-view data is crucial for tasks like behavioral analysis, although it traditional…
MeLo: Low-rank Adaptation is Better than Fine-tuning for Medical Image Diagnosis
Yitao Zhu, Zhenrong Shen, Zihao Zhao +5
The common practice in developing computer-aided diagnosis (CAD) models based on transformer architectures usually involves fine-tuning from ImageNet pre-trained weights. However,…
ChatCAD+: Towards a Universal and Reliable Interactive CAD using LLMs
Zihao Zhao, Sheng Wang, Jinchen Gu +6
The integration of Computer-Aided Diagnosis (CAD) with Large Language Models (LLMs) presents a promising frontier in clinical applications, notably in automating diagnostic process…
DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Task
Honglin Xiong, Sheng Wang, Yitao Zhu +5
The recent progress of large language models (LLMs), including ChatGPT and GPT-4, in comprehending and responding to human instructions has been remarkable. Nevertheless, these mod…