Matteo Bortoletto

Hi, I'm Matteo!

I'm a Research Engineer at kapa.ai (YC S23).

I did my PhD in the Collaborative AI group at the University of Stuttgart, advised by Prof. Andreas Bulling, with a focus on theory of mind in AI.

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

I hold a BSc and a MSc in Physics from the University of Padua.

LinkedIn   Scholar   GitHub  

Interests

My PhD focused on how AI can understand others' mental states such as beliefs, goals, preferences, and intentions — a concept known as theory of mind — and how this understanding can improve human–AI interaction. In particular, my work covers:

  • Designing and assessing AI models for theory of mind across vision and language [AAAI'24] [ACL'24] [ECAI'24] [RLC'26]
  • Probing and manipulating internal representations of mental states [EMNLP'25]
  • Stress-testing theory of mind on large foundation models [EMNLP'25]
  • Using theory of mind for action selection and intervention [ACL'26]
Publications
Preprints
Ontology-Guided Diffusion for Zero-Shot Visual Sim2Real Transfer
M Youssef, M Elfares, AM Meer, M Bortoletto, A Bulling
arXiv:2603.18719
[ArXiv]
Peer Reviewed
The Yokai Learning Environment: Tracking Beliefs Over Space and Time
C Ruhdorfer, M Bortoletto, J Forkel, J Foerster, A Bulling
RLC 2026
[ArXiv] [Code]
Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
C Ruhdorfer, M Bortoletto, V Oei, A Penzkofer, A Bulling
ICML 2026 (Spotlight, top 2.2%)
[ArXiv] [Code]
ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback
M Bortoletto, Y Zhou, L Ying, T Shu, A Bulling
ACL 2026 Findings
[ArXiv] [Website] [Code]
ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions
M Bortoletto, C Ruhdorfer, A Bulling
EMNLP 2025
[ArXiv] [Code] [Poster]
Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models
M Bortoletto, C Ruhdorfer, L Shi, A Bulling
EMNLP 2025 Findings · ICML 2024 Workshop on Mechanistic Interpretability
[ArXiv] [Code] [Poster] [OpenReview]
The Overcooked Generalisation Challenge
C Ruhdorfer, M Bortoletto, A Penzkofer, A Bulling
TMLR
[ArXiv] [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)
[ArXiv] [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
[Proceedings] [Code] [Poster]
Neural Reasoning about Agents' Goals, Preferences, and Actions
M Bortoletto, L Shi, A Bulling
AAAI 2024
[ArXiv] [Code] [Poster]
Improving Neural Saliency Prediction with a Cognitive Model of Human Visual Attention
E Sood, L Shi, M Bortoletto, Y Wang, P Müller, A Bulling
CogSci 2023
[Proceedings]
Exploring Natural Language Processing Methods for Interactive Behaviour Modelling
G Zhang, M Bortoletto, Z Hu, L Shi, M Bâce, A Bulling
INTERACT 2023
[ArXiv] [Code]

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

Personal: mabo22 [dot] lab [at] gmail [dot] com