Tewodros W. Ayalew

Email: tewodrosayalew [at] uchicago [dot] edu

I am a PhD student in Computer Science at the University of Chicago, advised by Dr. Matthew Walter at the Robot Intelligence through Perception Laboratory (RIPL) at the Toyota Technological Institute at Chicago (TTIC).

My research focuses on world models, with an emphasis on learning predictive representations of the physical world from visual experience. I am interested in learning latent actions, dynamics, and structured representations from in the wild human videos, with the goal of building generalizable world models that can understand, predict, and reason about how the world changes. Ultimately, I aim to move beyond curated datasets and controlled environments toward models that learn from diverse real world visual experience and transfer across tasks and embodiments.

Prior to my PhD, I earned an M.Sc. in Computer Science from the University of Saskatchewan, where I worked with Dr. Ian Stavness on unsupervised computer vision.