Search our Publications
Latest Publications
Stefan Menzel, Yew Soon Ong, Yaochu Jin, Niki van Stein, Anna Kononova, Thomas Bäck, Bernhard Sendhoff , "Special Session on Generative AI and Heuristic Optimization", IEEE Congress on Evolutionary Computation, 2026.
AbstractGenerative AI and Large Language Models are groundbreaking technological innovations with large impact on contemporary science and engineering by generating context-sensitive text, knowledge-based answers, software code, images, music, and 3D assets from text prompts and image inputs. Trained on large datasets, these models conserve knowledge, identify hidden patterns, and reason across diverse data modalities. In evolutionary computation, genera...
Download Bibtex file Per Mail Request
Tim Puphal , "A Survey of Robust Motion Planning: Interaction Modeling, Uncertainty Handling and Learning-Based Robustness ", IEEE International Conference on Intelligent Transportation Systems (ITSC), 2026.
AbstractAchieving robust autonomous driving remains a major challenge in translating research systems into widespread real-world deployment. Unlike scalable software technologies, autonomous vehicles must perform reliably across a wide range of conditions, including rare, safety-critical driving situations. This survey reviews research aimed at increasing the robustness of autonomous driving, with a particular focus on motion planning approaches that exp...
Download Bibtex file Per Mail Request
Johnson Zhou, Daniel Tanneberg, Forough Habibollahi, Alon Loeffler, Kiaran Lawson, Valentina Baccetti, Kwaku Dad Abu-Bonsrah, Candice Desouza, Finn Doensen, Bradley Watmuff, Daria Kornienko, Azin Azadi, Justin L. Bourke, Bernhard Sendhoff, Brett J. Kagan , "Embodied Neurocomputation: A Framework for Interfacing Biological Neural Cultures with Scaled Task-Driven Validation", arXiv, 2026.
AbstractBiological neural networks (BNNs) have been established as a powerful and adaptive substrate that offer the potential for incredibly energy and data efficient information processing with distinct learning mechanisms. Yet a core challenge to utilizing BNN for neurocomputation is determining the optimal encoding and decoding mechanisms between the traditional silicon computing interface and the living biology. Here, we propose an Embodied Neurocomp...
Download Bibtex file Per Mail Request
Fan Zhang and Michael Gienger , "Affordance-based Robot Manipulation with Flow Matching", ICRA 2026 Workshop on Semantics for Reliable Robot Autonomy: From Environment Understanding and Reasoning to Safe Interaction, 2026.
AbstractWe present a framework for assistive robot manipulation that addresses two fundamental challenges: efficient adaptation of large-scale models for scene affordance understanding and effective learning of robot actions by grounding the visual affordance. To tackle the first challenge, we adopt a parameter-efficient prompt tuning method, prepending learnable text prompts to a frozen vision model to predict affordances, while considering spatial and ...
Download Bibtex file Download PDF
Muhammad Ashfaq, Ahmed Sadik, Tommi Mikkonen, Muhammad Waseem, Niko Mäkitalo , "Runtime composition in dynamic system of systems: A systematic review of challenges, solutions, tools, and evaluation methods", Journal of Systems and Software, vol. 232, no. 112661, 2026.
AbstractSystem of Systems (SoS) represents a collection of constituent systems (CS) working together to achieve objectives unattainable by individual systems. With increasing relevance in domains such as smart cities, transportation, and robotics, the need for adaptable and dynamic SoS has emerged. Unlike traditional SoS architectures like UAF, DoDAF, and MODAF, which rely on static and manual integration, modern SoS demand dynamic, runtime assembly to m...
Download Bibtex file Download PDF
Jouh Yeong Chew, Alan Sarkisian, Christiane Wiebel, Christiane Attig, Zhaobo Zheng , "Workshop on Socially Aware and Cooperative Intelligent Systems", HAI '25: Proceedings of the 13th International Conference on Human-Agent Interaction, pp. 580-582, 2026.
AbstractIn an increasingly interconnected world, the role of intelligent systems is rapidly evolving beyond isolated decision-making and task execution. AI agents and systems are now expected not only to perform efficiently but also to engage responsibly within complex social environments. This workshop theme centers on the development of AI agents and systems that are capable of understanding, adapting to, and reacting to collaborate with humans in mea...
Download Bibtex file Download PDF
Matti Krüger, Yutaka Ooshima, Yu Fang , "Virtual Reflections on a Dynamic 2D Eye Model Improve Spatial Reference Identification", IEEE Transactions on Human-Machine Systems, 2026.
AbstractThe visible orientation of human eyes creates some transparency about people's spatial attention and other mental states. This leads to a dual role of the eyes as a means of sensing and communication. Accordingly, artificial eye models are being explored as communication media in human-machine interaction scenarios. One challenge in the use of eye models for communication consists of resolving spatial reference ambiguities, especially for screen...
Download Bibtex file Download PDF
Christiane Attig, Luisa Winzer, Tim Schrills, Mourad Zoubir, Maged Mortaga, Patricia Wollstadt, Christiane Wiebel, Thomas Franke , "Understanding successful human-AI teaming: The role of goal alignment and AI autonomy for social perception of LLM-based chatbots", Computers in Human Behavior: Artificial Humans, vol. 7, 2026.
AbstractLLM-based chatbots such as ChatGPT support collaborative, complex tasks by leveraging natural language processing to provide skills, knowledge, or resources beyond the user's immediate capabilities. Joint activity theory suggests that effective human-AI collaboration, however, requires more than responding to verbatim prompts—it depends on aligning with the user’s underlying goal. Since prompts may not always explicitly state the goal, an effecti...
Download Bibtex file Download PDF
Nergiz Yuca, Christian Internó, Nikolay Matyunin, Markus Olhofer, Barbara Hammer, Stefan Katzenbeisser , "PPFLex: Securing Non-IID Optimization in Federated Learning via MPC", FLCA@AAAI'26 - Workshop on Federated Learning for Critical Applications, 2026.
AbstractFederated Learning enables collaborative model training across multiple clients without sharing raw data, yet remains vulnerable to inference attacks. Optimizing FL for high performance and ensuring strong privacy guarantees are separate challenges, each requiring different approaches and trade-offs between efficiency, privacy and accuracy. Existing approaches often prioritize either model performance or privacy, failing to address both effective...
Download Bibtex file Download PDF
Nergiz Yuca, Nikolay Matyunin, Ektor Arzoglou, Nikolaos Athanasios Anagnostopoulos, Stefan Katzenbeisser , "A Survey on Privacy-Preserving Computing in the Automotive Domain", ACM Computing Surveys, vol. 58, 2026.
AbstractAs vehicles become increasingly connected and autonomous, they accumulate and manage various personal data, thereby presenting a key challenge in preserving privacy during data sharing and processing. This survey reviews applications of Secure Multi-Party Computation (MPC) and Homomorphic Encryption (HE) that address these privacy concerns in the automotive domain. First, we identify the scope of relevant use cases for these technologies, by su...
Download Bibtex file Download PDF
1 2 3 4 5 ... 181
Follow us
