Search our Publications
Latest Publications
Christian Internó, Elena Raponi, Markus Olhofer, Ali Raza, Thomas Bäck, Niki van Stein, Yaochu Jin, Barbara Hammer , "Pruning Federated Models through Loss Landscape Analysis and Client Agreement Scoring", IEEE Internet of Things Journal, 2026.
AbstractThe practical deployment of Federated Learning (FL) on resource-constrained devices is fundamentally limited by the high cost of training large models and the instability caused by heterogeneous (non-IID) client data. Conventional pruning methods often treat data heterogeneity as a problem to be mitigated. In this work, we introduce a paradigm shift: we reframe client diversity as a feature to be harnessed. We propose AutoFLIP, a framework that b...
Download Bibtex file Per Mail Request
Nils Einecke , "Conversational AI for Rapid Scientifi c Prototyping: A Case Study on ESA’s ELOPE Competition", arxiv, 2026.
AbstractLarge language models (LLMs) are increasingly used as coding partners, yet their role in accelerating scientific discovery remains underexplored. This paper presents a case study of using ChatGPT for rapid prototyping in ESA’s ELOPE (Event-based Lunar OPtical fl ow Egomotion estimation) competition. The competition required participants to process event camera data to estimate lunar lander trajectories. Despite joining late, we achieved second pl...
Download Bibtex file Per Mail Request
Leonard Hinckeldey, Elliot Fosong , Elle Miller, Rimvydas Rubavicius, Fan Zhang, Patricia Wollstadt, Stefano V. Albrecht, Subramanian Ramamoorthy , "Assistax: A Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics", 2026 Reinforcement Learning Conference, 2026.
AbstractThe development of reinforcement learning (RL) algorithms has been largely driven by ambitious challenge tasks and benchmarks. Games have dominated RL benchmarks because they present relevant challenges, are inexpensive to run and easy to understand. While games such as Go and Atari have led to many breakthroughs, they often do not directly translate to real-world embodied applications. In recognising the need to diversify RL benchmarks and addre...
Download Bibtex file
Matti Krüger , "Deictic Interfaces: More than Meets the Eye", Oxford University, Robotics Institute , 2026.
AbstractHuman visual perception provides a high data rate but is constrained by a narrow high-resolution field of view, creating a sequential processing bottleneck in complex environments. This talk explores how deictic interfaces can alleviate these constraints by communicating information via spatiotemporal relationships relative to the user, rather than through absolute references or symbolic descriptions. The first part examines a range of strategie...
Download Bibtex file Per Mail Request
Haiyue Yuan, Nikolay Matyunin, Ali Raza, Shujun Li , "LADFA: A Framework of Using Large Language Models and Retrieval-Augmented Generation for Personal Data Flow Analysis in Privacy Policies ", arXiv, 2026.
AbstractA privacy policy serves as an essential way to inform consumers about an organisation's data practises, including the collection, use, and sharing of personal data. Despite regulatory mandates such as GDPR, these privacy policies often remain difficult for consumers to fully comprehend due to the lengthy and complex legal language and inconsistent implementation. Previous research has applied machine learning and natural language processing techn...
Download Bibtex file Per Mail Request
Xavier Bonet-Monroig, Hao Wang, Adrián Pérez-Salinas , "Hierarchically discriminating Haar-randomness in quantum states from a black-box device", New Journal of Physics, vol. 28, no. 074512, 2026.
AbstractWe present a hierarchical discrimination algorithm for sets of states from a quantum d the compatibility of a set of quantum states $S$ with the $t$-moments of the Haar-random distribution over states. To check such compatibility, we consider the expectation values of states in $S$ with respect to a chosen observable, with focus on their statistical moments. Our first result is a connection between Haar-randomness and the Dirichlet distributio...
Download Bibtex file
Maria Bresich, Guenther Raidl, Caspian Coleman, Pascal Welke, Steffen Limmer , "Search Space Reduction Through Machine Learning for the Electric Autonomous Dial-A-Ride Problem", The 24th Conference of the International Federation of Operational Research Societies, 2026.
AbstractWe present a machine learning approach to improve the scalability of a state-of-the-art metaheuristic for the electric autonomous dial-a-ride problem. We explore graph sparsening techniques utilizing gradient boosted trees and a k-nearest neighbor heuristic to prune the search space by predicting and removing arcs unlikely to appear in good solutions. A significant performance boost of a large neighborhood search is achieved as demonstrated by re...
Download Bibtex file Per Mail Request
Maria Bresich, Guenther Raidl, Steffen Limmer , "Optimizing Dynamic Dispatching in Elevator Control with a Destination Registration System", International Conference on Computer Aided Systems Theory (Eurocast) 2026, 2026.
AbstractIn this work, we tackle the assignment and dispatching problem for an elevator group control system with a destination registration system (EGCS-DRS). Our considered system also allows for specifying the group size in case multiple people arrive together which further increases the practical complexity of this NP-complete problem. The goal is to minimize the average waiting time from requesting an elevator until entering it. We first address the...
Download Bibtex file Per Mail Request
Laurenz Tomandl, Maria Bresich, Guenther Raidl, Steffen Limmer , "A Learning Large Neighborhood Search for the Electric Autonomous Dial-A-Ride Problem", International Conference on Computer Aided Systems Theory (Eurocast) 2026, 2026.
AbstractIn this work, we explore improvements to the Electric Autonomous Dial-A-Ride Problem by introducing a Learning Large Neighborhood Search (LLNS) strategy. In contrast to previous studies that focused on sparsification or hyperparameter tuning via deep learning, our approach learns a function that evaluates how promising a route is for inclusion in the destroy set of the LNS. Specifically, we employ a route-wise destroy operation that removes entir...
Download Bibtex file Per Mail Request
Jan Petrossow , "Internship report - Human-AI Cooperative Design System Based on Generative Models", HRI-EU, 2026.
AbstractIn this project, the objective is to research novel approaches for the integration of multimodal Generative Artificial Intelligence (GenAI) models into industrial product development processes. More specifically, the plan is to identify the tools and potential users with which GenAI models interface during the ideation and design of a product, and to develop a prototypical system for generating 3D designs, which accounts for the interaction betwe...
Download Bibtex file Per Mail Request
1 ... 3 4 5 6 7 8 ... 183
Follow us
