Matteo Bortoletto

About

I am a PhD Student in the Collaborative AI group at the University of Stuttgart, Germany, advised by Prof. Andreas Bulling. My core research lies at the intersection of artificial intelligence and social cognition.

During my PhD, I've also spent some time as a Visiting Graduate Scholar at the SCAI Lab, Johns Hopkins University, advised by Prof. Tianmin Shu.

[Google Scholar] [GitHub] [X] [LinkedIn] [CV]

Research Interests

My research focuses on how AI can understand others' mental states such as desires, beliefs, and intentions โ€” a concept known as theory of mind โ€” and how this understanding can improve interactions between humans and AI. In particular, I work on:

News

Publications

Peer Reviewed

ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions
M Bortoletto, C Ruhdorfer, A Bulling
EMNLP 2025 [Paper] [Code]

Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models
M Bortoletto, C Ruhdorfer, L Shi, A Bulling
EMNLP 2025 Findings [Paper] [Code]
ICML 2024 Workshop on Mechanistic Interpretability [Paper] [Poster]

The Overcooked Generalisation Challenge
C Ruhdorfer, M Bortoletto, A Penzkofer, A Bulling
TMLR [Paper] [Code]

The Yokai Learning Environment: Tracking Beliefs Over Space and Time
C Ruhdorfer, M Bortoletto, A Bulling
IJCAI 2025 Workshop on Theory of Mind (Oral) [Paper] [Code]

Explicit Modelling of Theory of Mind for Belief Prediction in Nonverbal Social Interactions
M Bortoletto, C Ruhdorfer, L Shi, A Bulling
ECAI 2024 (Oral) [Paper] [Code]

Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition
M Bortoletto, C Ruhdorfer, A Abdessaied, L Shi, A Bulling
ACL 2024 [Paper] [Code] [Poster]

Neural Reasoning about Agents' Goals, Preferences, and Actions
M Bortoletto, L Shi, A Bulling
AAAI 2024 [Paper] [Code] [Poster]

Improving Neural Saliency Prediction with a Cognitive Model of Human Visual Attention
E Sood, L Shi, M Bortoletto, Y Wang, P Mรผller, A Bulling
CogSci 2023 [Paper]

Exploring Natural Language Processing Methods for Interactive Behaviour Modelling
G Zhang, M Bortoletto, Z Hu, L Shi, M Bรขce, A Bulling
INTERACT 2023 [Paper] [Code]

Preprints

Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
C Ruhdorfer, M Bortoletto, V Oei, A Penzkofer, A Bulling
arXiv:2508.06336 [Paper]

Contact

Email: matteo [dot] bortoletto [at] uni-stuttgart [dot] de

Office: SimTech Building, Room 01.027

Students

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