Yu Tian
Yu Tian is a postdoctoral researcher at the University of Pennsylvania. Prior to joining UPenn, he was a postdoctoral research fellow at Harvard University. He earned both his Ph.D. and his BSc with First Class Honours in computer science from the Australian Institute for Machine Learning (AIML) at the University of Adelaide.
Research
My primary research interests lie in computer vision and medical image analysis, focusing on trustworthy AI tasks such as abnormality and rarity learning, out-of-distribution detection, fairness learning, interpretability, and federated learning, with an emphasis on their biomedical applications. Recently, I’ve also been exploring the development of multi-modal medical foundation models and studying their trustworthiness.News
| One paper on fairness under domain shift is accepted to ECCV 2024. Check out the paper and dataset here. | |
| Two recent papers are accepted to Medical Image Analysis. One about artifact correction and another about malignant breast lesion detection. | |
| One paper is accepted to IEEE Transactions on Medical Imaging (TMI). | |
| Two papers are accepted to CVPR2024. | |
| One paper on OoD detection for NLP systems is accepted in COLING2024. | |
| Two papers are accepted in ICLR2024. One about fairness learning and another about zero-shot anomaly detection. |
