Matteo Bortoletto

Institute for Visualisation and Interactive Systems, University of Stuttgart

+49 711 685 60147 Pfaffenwaldring 5a, 70569 Stuttgart, Germany University of Stuttgart, SimTech Building, Room 01.027 Google Scholar

Biography

Matteo Bortoletto is a PhD student in the Perceptual User Interfaces group since February 2022. He holds a Bachelor’s degree in Physics and a Master’s degree in Physics of Data from the University of Padua. His research interests include reinforcement learning, multi-agent systems and machine theory of mind.

Open Thesis Projects

 

Theory of Mind in Collaborative EnvironmentsMaster

 

Theory of Mind Modelling in Symmetric Multi-Agent EnvironmentsMaster

 

Neural Reasoning with cognitively-inspired RepresentationsMaster

 

A Vector Symbolic Algebra for Language ModelsMaster

Teaching

2023

Machine Perception and Learning (Tutor)Master

2022

Machine Perception and Learning (Tutor)Master

---

Supervision

2024

Multimodal LLM for Theory of Mind Modeling in Collaborative Tasks (M.Sc.) Jan-Philip Thewes

2023

Into the Minds of the Chefs: Using Theory of Mind for Robust Collaboration with Humans in Overcooked (M.Sc.) Constantin Ruhdorfer

 

Transformer Based Architecture for Belief Prediction in Object-Context Scenarios (M.Sc. research Ppoject) John Pravin Arockiasamy

 

Recreating False-Belief Tests as Visual Question Answering Tasks (M.Sc.) Michael Erdemann**

**Co-supervised with Susanne Hindennach

---

Publications

(Bortoletto et al., 2024; Bortoletto et al., 2024; Bortoletto et al., 2024; Bortoletto et al., 2024; Ruhdorfer et al., 2024; Zhang et al., 2023; Sood et al., 2023)

1. Explicit Modelling of Theory of Mind for Belief Prediction in Nonverbal Social Interactions

   Matteo Bortoletto, Constantin Ruhdorfer, Lei Shi, Andreas Bulling

   Proc. 27th European Conference on Artificial Intelligence (ECAI), pp. 1–8, 2024.

   Abstract Links BibTeX Project

   We propose MToMnet - a Theory of Mind (ToM) neural network for predicting beliefs and their dynamics during human social interactions from multimodal input. ToM is key for effective nonverbal human communication and collaboration, yet, existing methods for belief modelling have not included explicit ToM modelling or have typically been limited to one or two modalities. MToMnet encodes contextual cues (scene videos and object locations) and integrates them with person-specific cues (human gaze and body language) in a separate MindNet for each person. Inspired by prior research on social cognition and computational ToM, we propose three different MToMnet variants: two involving fusion of latent representations and one involving re-ranking of classification scores. We evaluate our approach on two challenging real-world datasets, one focusing on belief prediction, while the other examining belief dynamics prediction. Our results demonstrate that MToMnet surpasses existing methods by a large margin while at the same time requiring a significantly smaller number of parameters. Taken together, our method opens up a highly promising direction for future work on artificial intelligent systems that can robustly predict human beliefs from their non-verbal behaviour and, as such, more effectively collaborate with humans.

   doi:

   @inproceedings{bortoletto24_ecai, author = {Bortoletto, Matteo and Ruhdorfer, Constantin and Shi, Lei and Bulling, Andreas}, title = {Explicit Modelling of Theory of Mind for Belief Prediction in Nonverbal Social Interactions}, booktitle = {Proc. 27th European Conference on Artificial Intelligence (ECAI)}, year = {2024}, pages = {1--8}, doi = {} }
2. 

   Benchmarking Mental State Representations in Language Models

   Matteo Bortoletto, Constantin Ruhdorfer, Lei Shi, Andreas Bulling

   Proc. ICML 2024 Workshop on Mechanistic Interpretability, pp. 1–21, 2024.

   Abstract Links BibTeX Project

   While numerous works have assessed the generative performance of language models (LMs) on tasks requiring Theory of Mind reasoning, research into the models’ internal representation of mental states remains limited. Recent work has used probing to demonstrate that LMs can represent beliefs of themselves and others. However, these claims are accompanied by limited evaluation, making it difficult to assess how mental state representations are affected by model design and training choices. We report an extensive benchmark with various LM types with different model sizes, fine-tuning approaches, and prompt designs to study the robustness of mental state representations and memorisation issues within the probes. Our results show that the quality of models’ internal representations of the beliefs of others increases with model size and, more crucially, with fine-tuning. We are the first to study how prompt variations impact probing performance on theory of mind tasks. We demonstrate that models’ representations are sensitive to prompt variations, even when such variations should be beneficial. Finally, we complement previous activation editing experiments on Theory of Mind tasks and show that it is possible to improve models’ reasoning performance by steering their activations without the need to train any probe.

   doi:

   Paper: bortoletto24_icmlw.pdf

   Code: https://git.hcics.simtech.uni-stuttgart.de/public-projects/mental-states-in-LMs

   Paper Access: https://openreview.net/forum?id=yEwEVoH9Be

   @inproceedings{bortoletto24_icmlw, author = {Bortoletto, Matteo and Ruhdorfer, Constantin and Shi, Lei and Bulling, Andreas}, title = {Benchmarking Mental State Representations in Language Models}, booktitle = {Proc. ICML 2024 Workshop on Mechanistic Interpretability}, year = {2024}, pages = {1--21}, doi = {}, url = {https://openreview.net/forum?id=yEwEVoH9Be} }
3. 

   Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition

   Matteo Bortoletto, Constantin Ruhdorfer, Adnen Abdessaied, Lei Shi, Andreas Bulling

   Proc. 62nd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 1–16, 2024.

   Abstract Links BibTeX Project

   Recent work on dialogue-based collaborative plan acquisition (CPA) has suggested that Theory of Mind (ToM) modelling can improve missing knowledge prediction in settings with asymmetric skill-sets and knowledge. Although ToM was claimed to be important for effective collaboration, its real impact on this novel task remains under-explored. By representing plans as graphs and by exploiting task-specific constraints we show that, as performance on CPA nearly doubles when predicting one’s own missing knowledge, the improvements due to ToM modelling diminish. This phenomenon persists even when evaluating existing baseline methods. To better understand the relevance of ToM for CPA, we report a principled performance comparison of models with and without ToM features. Results across different models and ablations consistently suggest that learned ToM features are indeed more likely to reflect latent patterns in the data with no perceivable link to ToM. This finding calls for a deeper understanding of the role of ToM in CPA and beyond, as well as new methods for modelling and evaluating mental states in computational collaborative agents.

   doi:

   Paper: bortoletto24_acl.pdf

   Code: https://git.hcics.simtech.uni-stuttgart.de/public-projects/limits-of-tom

   @inproceedings{bortoletto24_acl, author = {Bortoletto, Matteo and Ruhdorfer, Constantin and Abdessaied, Adnen and Shi, Lei and Bulling, Andreas}, title = {Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition}, booktitle = {Proc. 62nd Annual Meeting of the Association for Computational Linguistics (ACL)}, year = {2024}, pages = {1--16}, doi = {} }
4. 

   Neural Reasoning About Agents’ Goals, Preferences, and Actions

   Matteo Bortoletto, Lei Shi, Andreas Bulling

   Proc. 38th AAAI Conference on Artificial Intelligence (AAAI), pp. 456–464, 2024.

   Abstract Links BibTeX Project

   We propose the Intuitive Reasoning Network (IRENE) – a novel neural model for intuitive psychological reasoning about agents’ goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph neural network for learning agent and world state representations with a transformer to encode the task context. When evaluated on the challenging Baby Intuitions Benchmark, IRENE achieves new state-of-the-art performance on three out of its five tasks – with up to 48.9 % improvement. In contrast to existing methods, IRENE is able to bind preferences to specific agents, to better distinguish between rational and irrational agents, and to better understand the role of blocking obstacles. We also investigate, for the first time, the influence of the training tasks on test performance. Our analyses demonstrate the effectiveness of IRENE in combining prior knowledge gained during training for unseen evaluation tasks.

   doi: 10.1609/aaai.v38i1.27800

   Paper: bortoletto24_aaai.pdf

   Code: https://git.hcics.simtech.uni-stuttgart.de/public-projects/IRENE

   @inproceedings{bortoletto24_aaai, author = {Bortoletto, Matteo and Shi, Lei and Bulling, Andreas}, title = {Neural Reasoning About Agents’ Goals, Preferences, and Actions}, booktitle = {Proc. 38th AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, volume = {38}, number = {1}, pages = {456--464}, doi = {10.1609/aaai.v38i1.27800} }

1. 

   The Overcooked Generalisation Challenge

   Constantin Ruhdorfer, Matteo Bortoletto, Anna Penzkofer, Andreas Bulling

   arxiv:2406.17949, pp. 1-25, 2024.

   Abstract Links BibTeX Project

   We introduce the Overcooked Generalisation Challenge (OGC) - the first benchmark to study agents’ zero-shot cooperation abilities when faced with novel partners and levels in the Overcooked-AI environment. This perspective starkly contrasts a large body of previous work that has trained and evaluated cooperating agents only on the same level, failing to capture generalisation abilities required for real-world human-AI cooperation. Our challenge interfaces with state-of-the-art dual curriculum design (DCD) methods to generate auto-curricula for training general agents in Overcooked. It is the first cooperative multi-agent environment specially designed for DCD methods and, consequently, the first benchmarked with state-of-the-art methods. It is fully GPU-accelerated, built on the DCD benchmark suite minimax, and freely available under an open-source license: this https URL. We show that current DCD algorithms struggle to produce useful policies in this novel challenge, even if combined with recent network architectures that were designed for scalability and generalisability. The OGC pushes the boundaries of real-world human-AI cooperation by enabling the research community to study the impact of generalisation on cooperating agents.

   Code: https://git.hcics.simtech.uni-stuttgart.de/public-projects/OGC

   Paper Access: https://arxiv.org/abs/2406.17949

   @techreport{ruhdorfer2024_arxiv, title = {The Overcooked Generalisation Challenge}, author = {Ruhdorfer, Constantin and Bortoletto, Matteo and Penzkofer, Anna and Bulling, Andreas}, year = {2024}, pages = {1-25}, url = {https://arxiv.org/abs/2406.17949} }

1. 

   Exploring Natural Language Processing Methods for Interactive Behaviour Modelling

   Guanhua Zhang, Matteo Bortoletto, Zhiming Hu, Lei Shi, Mihai Bâce, Andreas Bulling

   Proc. IFIP TC13 Conference on Human-Computer Interaction (INTERACT), pp. 1–22, 2023.

   Abstract Links BibTeX Project Best Student Paper Nomination

   Analysing and modelling interactive behaviour is an important topic in human-computer interaction (HCI) and a key requirement for the development of intelligent interactive systems. Interactive behaviour has a sequential (actions happen one after another) and hierarchical (a sequence of actions forms an activity driven by interaction goals) structure, which may be similar to the structure of natural language. Designed based on such a structure, natural language processing (NLP) methods have achieved groundbreaking success in various downstream tasks. However, few works linked interactive behaviour with natural language. In this paper, we explore the similarity between interactive behaviour and natural language by applying an NLP method, byte pair encoding (BPE), to encode mouse and keyboard behaviour. We then analyse the vocabulary, i.e., the set of action sequences, learnt by BPE, as well as use the vocabulary to encode the input behaviour for interactive task recognition. An existing dataset collected in constrained lab settings and our novel out-of-the-lab dataset were used for evaluation. Results show that this natural language-inspired approach not only learns action sequences that reflect specific interaction goals, but also achieves higher F1 scores on task recognition than other methods. Our work reveals the similarity between interactive behaviour and natural language, and presents the potential of applying the new pack of methods that leverage insights from NLP to model interactive behaviour in HCI.

   Paper: zhang23_interact.pdf

   @inproceedings{zhang23_interact, title = {Exploring Natural Language Processing Methods for Interactive Behaviour Modelling}, author = {Zhang, Guanhua and Bortoletto, Matteo and Hu, Zhiming and Shi, Lei and B{\^a}ce, Mihai and Bulling, Andreas}, booktitle = {Proc. IFIP TC13 Conference on Human-Computer Interaction (INTERACT)}, pages = {1--22}, year = {2023}, publisher = {Springer} }
2. 

   Improving Neural Saliency Prediction with a Cognitive Model of Human Visual Attention

   Ekta Sood, Lei Shi, Matteo Bortoletto, Yao Wang, Philipp Müller, Andreas Bulling

   Proc. the 45th Annual Meeting of the Cognitive Science Society (CogSci), pp. 3639–3646, 2023.

   Abstract Links BibTeX Project

   We present a novel method for saliency prediction that leverages a cognitive model of visual attention as an inductive bias. This approach is in stark contrast to recent purely data-driven saliency models that achieve performance improvements mainly by increased capacity, resulting in high computational costs and the need for large-scale training datasets. We demonstrate that by using a cognitive model, our method achieves competitive performance to the state of the art across several natural image datasets while only requiring a fraction of the parameters. Furthermore, we set the new state of the art for saliency prediction on information visualizations, demonstrating the effectiveness of our approach for cross-domain generalization. We further provide augmented versions of the full MSCOCO dataset with synthetic gaze data using the cognitive model, which we used to pre-train our method. Our results are highly promising and underline the significant potential of bridging between cognitive and data-driven models, potentially also beyond attention.

   Paper: sood23_cogsci.pdf

   Code: https://git.hcics.simtech.uni-stuttgart.de/public-projects/neural-saliency-prediction-with-a-cognitive-model/

   Supplementary Material: sood23_cogsci_sup.pdf

   Dataset: https://perceptualui.org/research/datasets/MSCOCOEMMAFigureQAEMMA/

   @inproceedings{sood23_cogsci, author = {Sood, Ekta and Shi, Lei and Bortoletto, Matteo and Wang, Yao and Müller, Philipp and Bulling, Andreas}, title = {Improving Neural Saliency Prediction with a Cognitive Model of Human Visual Attention}, booktitle = {Proc. the 45th Annual Meeting of the Cognitive Science Society (CogSci)}, year = {2023}, pages = {3639--3646} }