Search our Publications
Latest Publications
Christian Internó, Jumpei Yamaguchi, Markus Olhofer, David Klindt, Barbara Hammer , "The Observer Effect in World Models: Invasive Adaptation Corrupts Latent Physics", ArXiv, 2026.
AbstractDetermining whether neural models internalize physical laws as world models, rather than exploiting statistical shortcuts, remains challenging, especially under out-of-distribution (OOD) shifts. Standard evaluations often test latent capability via downstream adaptation (e.g., fine-tuning or high-capacity probes), but such interventions can change the representations being measured and thus confound what was learned during self-supervised learnin...
Download Bibtex file Per Mail Request
Jörg Deigmöller, Nakul Agarwal, Stephan Hasler, Daniel Tanneberg, Chao Wang, Reza Ghoddoosian, Felix Ocker, Anna Belardinelli, Fan Zhang, Behzad Dariush, Michael Gienger , "MERGE: Guided Vision-Language Models for Multi-Actor Event Reasoning and Grounding in Human–Robot Interaction", ICRA, 2026.
AbstractWe introduce MERGE, a system for situational grounding of actors, objects, and events in dynamic hu- man–robot group interactions. Effective collaboration in such settings requires consistent situational awareness, built on persistent representations of people and objects and an episodic abstraction of events. MERGE achieves this by uniquely iden- tifying physical instances of actors (humans or robots) and objects and structuring them into...
Download Bibtex file Per Mail Request
Andrea Moleri, Christian Internó, Ali Raza, Markus Olhofer, David Klindt, Barbara Hammer , "FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios", ArXIv, 2026.
AbstractFederated Learning (FL) enables distributed optimization without compromising data sovereignty. Yet, where local label distributions are mutually exclusive, standard weight aggregation fails due to conflicting optimization trajectories. Often, FL methods rely on pretrained foundation models, introducing unrealistic assumptions. We introduce FederatedFactory, a zero-dependency framework that inverts the unit of federation from discriminative param...
Download Bibtex file Per Mail Request
Tom Hitron, Thomas H Weisswange, Guy Doron, Hadas Erel , "Designing Robotic Behavior for Promoting Positive Human-Human Interactions in Challenging Environments: A Research Agenda for Leveraging Modeling and Carryover Effects", 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI 2026): Workshop on Robots for Communities, 2026.
AbstractRobots are increasingly integrated into public environments for functional and technical purposes, yet once positioned in shared human spaces they also have inevitable social impact that can shape how people behave, interact with them, and interact with one another. We present a framework for using minimal robotic behavior to foster a more positive social atmosphere in emotionally challenging environments, with a focus on hospitals. Building on e...
Download Bibtex file Per Mail Request
Christiane Attig, Alan Sarkisian, Jouh Yeong Chew, Christiane Wiebel , "Beyond Reciprocity: Psychological Needs as a Foundation for Human-AI Cooperation", HAI '25: Proceedings of the 13th International Conference on Human-Agent Interaction, pp. 445-448, 2026.
AbstractArtificial Intelligence (AI) systems are becoming increasingly pervasive in our daily lives. As these systems are applied across a wide range of domains, the need to thoughtfully design successful cooperative human-machine interaction becomes more relevant than ever. In this rapidly evolving sociotechnological landscape, what counts as “successful” human-AI cooperation from the human perspective remains an open question. We here argue that design...
Download Bibtex file Download PDF
Antonello Ceravola , "Workshop on Artificial Intelligence and usage of AI in school", Liceo Statale Galileo Galilei di Verona, Liceo Statale Galileo Galilei di Verona, 2026.
AbstractArtificial Intelligence is increasingly present in our daily lives, often surrounded by excitement, curiosity, skepticism, and sometimes fear. This talk explores different perspectives on AI, helping the audience understand what we really mean by “intelligence” and how AI compares to human reasoning. Through simple reflections, psychological experiments, and practical demonstrations, the presentation examines how AI works, where it is already be...
Download Bibtex file Per Mail Request
Aimée Sousa Calepso, Anna Belardinelli, Valerie Behrwind, Christine Knoll, Sarah B. Blakeslee, Bernhard Sendhoff , "Toward automated interactions for pediatric inpatients using a social robot", 21st ACM/IEEE International Conference on Human-Robot Interaction (HRI 2026): Workshop on Robots for Care, 2026.
AbstractWe report on the deployment of the Haru social robot in a pediatric oncology ward to reduce social isolation and detail the main challenges faced during the process. We started with a semi-scripted interaction to gain insights about potential technical and psycho-social issues with such sensitive population, before moving to more flexible and automated conversations. We placed the robot in patients' single rooms and tested simple dialogues, after...
Download Bibtex file Per Mail Request
Ali Raza, Gaurang Gupta, Nikolay Matyunin, Jibesh Patra , "Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models", arXiv, 2026.
AbstractWarning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content such as generating sophisticated phishing emails and assisting in writing code of harmful computer viruses. Thus, it is crucial to ensure their safe and responsible response generation. To reduce the risk of generating harmful or ir...
Download Bibtex file Per Mail Request
Tuan Vu Pham, Judith Dörrenbächer, Thomas H Weisswange, Marc Hassenzahl , "“Who Owns the Robot Matters!” – How Robot Ownership Shapes Belonging and Social Roles in Human Groups", ACM Designing Interactive Systems (DIS 2026), 2026.
AbstractRobot ownership is not just a background detail but a powerful social signal. Especially in settings where a robot mediates a group of people, ownership may profoundly impact social dynamics. In the present study, participants (n = 220) saw one of five videos in which a robot was introduced as being owned by either (1) a faceless outgroup entity, (2) an active ingroup speaker, (3) a passive ingroup peer, (4) the participants themselves, or (5) th...
Download Bibtex file Download PDF
Andrea Moleri, Christian Internó, Ali Raza, Markus Olhofer, Barbara Hammer , "Geodesic-SVDD Latent Mixup for Distributed Learning", International Joint Conference on Neural Networks (IJCNN 2026), 2026.
AbstractFederated Learning (FL) offers a privacy-enhancing paradigm for distributed learning; however, training One-Class Classifiers (OCC) such as Deep Support Vector Data Description (Deep SVDD) in distributed settings remains challenging due to statistical heterogeneity (Non-IID data) and the risk of local mode collapse. This paper presents a novel Federated Deep SVDD framework designed to enforce a compact, hyperspherical description of normal data a...
Download Bibtex file Per Mail Request
1 2 3 ... 181
Follow us
