Tsung-Yu Lin

I am a Research Scientist at Meta, where my work centers on image and video representation learning as well as vision-language modeling. Prior to joining Meta, I completed my doctoral studies in the Computer Vision Lab at the University of Massachusetts Amherst under the supervision of Prof. Subhransu Maji.

My research aims to advance the development of AI systems capable of interpreting and interacting with the physical world to support people in their everyday lives. I am particularly interested in semantic visual representations learning, fine-grained visual understanding, geometric modeling, temporal reasoning, and building systems that robustly generalize to real-world environments.

I am fortunate to have collaborated with numerous distinguished researchers and interns in the fields of machine learning and artificial intelligence. Additional information can be found in my CV and Google Scholar profile.