I’m a PhD student at the University of Tübingen and the International Max Planck Research School for Intelligent Systems (IMPRS-IS), under the supervision of Seong Joon Oh.

I’m primarily interested in enhancing the generalization capabilities of current machine learning systems. This involves learning robust representations from raw data and using them in a way that accurately reflects data generative processes. I believe that mimicking the structure of the real-world in our models, both in how we learn representations and in how we use them, is a key part of making progress towards trustworthy systems.

During my undergraduate studies in Computer Science at Kaunas University of Technology, I had the opportunity to study various flavors of Recurrent Neural Networks (RNNs). For my Master’s degree in Machine Learning from the University of Tübingen, I focused on reinforcement learning, particularly in the context of zero-shot generalization.

I’m always open to potential collaborations or discussions - feel free to reach out!