I am a PhD Student in Computer Science at the University of Stuttgart, Germany, advised by Prof. Andreas Bulling. My research focuses on computational theory of mind, with a specific emphasis on deep learning approaches. In my work, I design and assess innovative AI models for theory of mind tasks that span multiple modalities, including vision, natural language, gaze, and pose. My ultimate goal is to improve human-AI collaboration. For some reason, I end up using graph neural networks in every project I work on. I hold a BSc degree in Physics and a MSc degree in Physics of Data from the University of Padua, Italy (where Galileo taught and the first woman got a PhD!). During my studies I focused on theoretical physics, in particular theoretical ecology and neuroscience.

News

• [25.03.2024] 👨🏼‍🏫 Constantin Ruhdofer, Anna Penzkofer and I are organising a practical course “Computational Theory of Mind and Cognition”. Our course has limited spots available, don’t miss out on this opportunity!
• [01.03.2024] 🏆 My student Constantin Ruhdorfer’s master’s thesis was awarded the Rul Gunzenhäuser Award
• [09.12.2023] 🔥 Paper accepted at AAAI 2024 (Vancouver, Canada)
• [29.09.2023] 📑 Reviewing for CHI 2024
• [07.04.2023] 🔥 Paper accepted at CogSci 2023 (Sydney, Australia)
• [27.03.2023] 🔥 Paper accepted at INTERACT 2023 (York, UK)

Publications

What’s floating my boat these days?

• Probing internal representations in large language models
• Building causal models for planning using theory of mind
• Learning theory of mind through world models

Supervision

I regulary supervise Master and Bachelor theses, if you have an idea for a thesis feel free to email me. If you are looking for available projects, check if there are Open Thesis Projects here.

More about me

• Ideal setup: MacBook Air, coffee, my Beholder, and a mini zen garden that I keep rearranging instead of meditating
• King Gizz aficionado with a growing vinyl collection
• Always reading: “The Hobbit” - I highly recommend the edition illustrated by Jemima Catlin.
• If you work at Meta, you may call me [1, 5345, 371, 29877] or leave out the 1, no need to be that formal. If you are at Anthropic, it could be [5236, 51289]. If you work at Google, perhaps [2, 162860] or simply [162860]. At OpenAI, it would be [11836, 668, 78].
• My favorite Pokémon is Espeon
• Powdered sugar is evil
• I don’t believe in umbrellas
• I used to hate pear juice, but since I turned 18, I drink it very willingly, so much so that it’s entered my top 3