Marcel Mross

Christian Deppe, Eduard Jorswieck, Pin-Hsun Lin et al.

The Foundations of Future Communication Systems (FFCS) conference brought together leading researchers from information theory, quantum communication, molecular communication, semantic communication, and secure network design to explore the fundamental principles shaping next-generation communication systems. The event serves as a platform for interdisciplinary exchange, bridging classical Shannon theory, post-Shannon paradigms, quantum information science, and emerging physically grounded communication models. This report compiles the abstracts of all invited talks, contributed presentations, and poster contributions presented at FFCS. The collected works reflect the breadth of contemporary research directions, including identification-based communication, entanglement-assisted networks, semantic and goal-oriented communication, coding for molecular and nanoscale systems, secure authentication mechanisms, and information-theoretic limits of novel physical-layer architectures. A central theme of the conference was the re-examination of foundational limits under realistic physical, architectural, and security constraints. Many contributions move beyond traditional rate-centric perspectives and instead investigate reliability, identification, semantics, resource efficiency, and trust in complex and heterogeneous networks. The inclusion of poster abstracts further highlights emerging ideas, early-stage research results, and innovative cross-disciplinary approaches that contribute to shaping future communication paradigms. By documenting the intellectual landscape presented at FFCS, this report aims to provide a structured overview of current research frontiers and to stimulate continued collaboration across theoretical and experimental domains.

Marvin Klingner, Andreas Bär, Marcel Mross et al.

In this work we address the task of observing the performance of a semantic segmentation deep neural network (DNN) during online operation, i.e., during inference, which is of high importance in safety-critical applications such as autonomous driving. Here, many high-level decisions rely on such DNNs, which are usually evaluated offline, while their performance in online operation remains unknown. To solve this problem, we propose an improved online performance prediction scheme, building on a recently proposed concept of predicting the primary semantic segmentation task's performance. This can be achieved by evaluating the auxiliary task of monocular depth estimation with a measurement supplied by a LiDAR sensor and a subsequent regression to the semantic segmentation performance. In particular, we propose (i) sequential training methods for both tasks in a multi-task training setup, (ii) to share the encoder as well as parts of the decoder between both task's networks for improved efficiency, and (iii) a temporal statistics aggregation method, which significantly reduces the performance prediction error at the cost of a small algorithmic latency. Evaluation on the KITTI dataset shows that all three aspects improve the performance prediction compared to previous approaches.