Yuhao Zhang
2 papers · Latest:
Robotics
RedVLA: Physical Red Teaming for Vision-Language-Action Models
This paper introduces RedVLA, the first physical red teaming framework for VLA models, to proactively detect and mitigate real-world safety risks.
2604.22591
Computer VisionContrastive Learning of Medical Visual Representations from Paired Images and Text
ConVIRT is an unsupervised contrastive learning method that leverages paired medical images and their descriptive text to learn superior visual representations, significantly improving data efficiency and performance on medical imaging tasks.
2010.00747
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.