38 citations · 39 across the 5 of their papers we have counts for
5 papers
More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
Chengzhi Liu, Zhongxing Xu, Qingyue Wei +5
Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. Howe…
RetinaRegNet: A Zero-Shot Approach for Retinal Image Registration
Vishal Balaji Sivaraman, Muhammad Imran, Qingyue Wei +7
We introduce RetinaRegNet, a zero-shot image registration model designed to register retinal images with minimal overlap, large deformations, and varying image quality. RetinaRegNe…
Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding
Zhiheng Cheng, Qingyue Wei, Hongru Zhu +4
The Segment Anything Model (SAM) has garnered significant attention for its versatile segmentation abilities and intuitive prompt-based interface. However, its application in medic…
3D TransUNet: Advancing Medical Image Segmentation through Vision Transformers
Jieneng Chen, Jieru Mei, Xianhang Li +12
Medical image segmentation plays a crucial role in advancing healthcare systems for disease diagnosis and treatment planning. The u-shaped architecture, popularly known as U-Net, h…
L2B: Learning to Bootstrap Robust Models for Combating Label Noise
Yuyin Zhou, Xianhang Li, Fengze Liu +6
Deep neural networks have shown great success in representation learning. However, when learning with noisy labels (LNL), they can easily overfit and fail to generalize to new data…