Mert Albaba

bio

I am a PhD student at ETH Zürich and the Max Planck Institute – Perceiving Systems, co-advised by Michael Black and Andreas Krause. My primary research interests span imitation learning, diffusion models and VLMs. I am especially excited about creating generative methods that enable robots to learn human skills from videos. I am an ELLIS PhD Student and a CLS Fellow.

I previously spent a year at USC, earned my MSc in Mechanical Engineering at Bilkent University under the supervision of Yildiray Yildiz, and completed my BSc in Electrical and Computer Engineering at Bilkent University.

Download my CV

research

My primary focus is on generative imitation learning: integrating ideas from video diffusion models, imitation learning, and VLMs to create methods that can accurately mimic human skills in a generative way. I’m particularly interested in both robotics and realistic avatar animation (e.g., character simulation). Ultimately, I aim to enable humanoid agents —virtual or physical— to master a wide range of tasks by learning from just a handful of demonstrations or even from raw video data alone.

In addition to my work in generative imitation learning, I have five years of experience applying reinforcement learning and game theory to model human behavior in autonomous driving. I remain strongly interested in multi-agent systems, where game-theoretic principles can enhance both reinforcement and imitation learning.