Aug 2026· Zenodo (CERN European Organization for Nuclear Research)
Abstract
Praktisch nutzbare Künstliche Intelligenz entstand aus dem Bündnis kluger Köpfe mit den rechentechnischen Fähigkeiten Boolescher Automaten – natürliche Intelligenz dagegen aus Selbstorganisation und Evolution. Dieser zweite Weg rückt mit dem neuromorphen Rechnen zunehmend wieder in das Blickfeld von Wissenschaft und Praxis: Spikende neuronale Netze (SNN) stellen dem wachsenden Energiehunger moderner KI-Systeme eine reale Alternative entgegen und erweitern das Methodenrepertoire der KI um Elemente der Selbstorganisation. Das vorliegende Werk erläutert dieses Spannungsfeld allgemeinverständlich und zugleich mathematisch nachvollziehbar. Am Beispiel des Texterzeugungsmoduls von ChatGPT werden Konzept, Eleganz und Aufwand der modernen Transformer-basierten KI Schritt für Schritt sichtbar gemacht und mit den Kodierungs-, Lern- und Netzgestaltungsmethoden spikender neuronaler Netze verglichen. Den Hintergrund bilden ausgewählte Wirkungsmechanismen des menschlichen Nervensystems – die kybernetischen Vorbilder des neuromorphen Rechnens. Behandelt werden u. a. Spike-Timing-Dependent Plasticity, Populations- und Zeitkodierung, das Neural Engineering Framework, neuromorphe Hardware von Loihi 2 bis zu kommerziellen Edge-Prozessoren sowie die Perspektiven der wechselseitigen Befruchtung klassischer und neuromorpher KI – bis hin zum optischen Rechnen. (ca. 90 Seiten, 20 Abbildungen) English abstract: Practically usable artificial intelligence arose from the alliance of ingenious minds with the computational power of Boolean automata – natural intelligence, by contrast, from self-organization and evolution. With neuromorphic computing, this second path is moving back into the focus of science and engineering: spiking neural networks (SNN) offer a real alternative to the growing energy appetite of modern AI systems and fundamentally extend the methodological repertoire of AI by elements of self-organization. This monograph (in German) explains this field of tension in a generally accessible yet mathematically traceable way. Using the text-generation module of ChatGPT as a representative example, the concept, elegance and computational cost of modern transformer-based AI are made visible step by step and compared with the coding, learning and network-design methods of spiking neural networks. The background is provided by selected mechanisms of the human nervous system – the cybernetic archetypes of neuromorphic computing. Topics include spike-timing-dependent plasticity, population and temporal coding, the Neural Engineering Framework, neuromorphic hardware from Loihi 2 to commercial edge processors, and the prospects of mutual enrichment of classical and neuromorphic AI – up to optical computing. (approx. 90 pages, 20 figures)
This paper investigates a dynamic heterogeneous mobile edge computing network (HMECN), where mobile devices (MDs) could offload their full tasks to a small base station (SBS) directly or the macro base station (MBS) in direct or relay mode. As age of information (AoI) is a comprehensive and accurate metric to capture the freshness of computation results, we formulate a long-term weighted sum AoI (LWSA) minimization problem in the HMECN by jointly optimizing the offloading decisions of MDs as well as the bandwidth and computation resource allocation of all base stations, subject to energy, delay and peak AoI constraints. To address the formulated non-convex mixed integer nonlinear programming problem, we decompose it into the offloading decision optimization (ODO) top-problem and the resource allocation optimization (RAO) sub-problem. Based on the decomposition, we propose a federated learning (FL)-assisted hybrid DRL and convex approach that is comprised of a safe multi-agent DRL algorithm, convex optimization and FL. The ODO top-problem is solved by the safe multi-agent DRL algorithm, which strictly ensures that the actions of each agent do not exceed its energy constraint and then paves the way for using convex optimization to solve the RAO sub-problem. FL is used to alleviate the training instability problem aggravated by multi-agent settings via breaking the limitation of partial knowledge for each individual agent. Simulation results demonstrate the superiority of the proposed approach in terms of the LWSA, convergence, scalability and robustness in dynamic environments.
Xiaoying Liu, Junhao Zheng, Kechen Zheng et al.· IEEE Transactions on Mobile...· 8 citations
High-altitude airships (HAS) and uncrewed aerial vehicles (UAVs) equipped with Multiaccess Edge Computing (MEC) servers have emerged as promising aerial MEC nodes for providing task offloading (TO) services to intelligent mobile devices (IMDs) in post-disaster scenarios. HAS offers robust computing and energy resources, while UAVs provide flexible, low-altitude coverage for rapid deployment. However, direct task offloading from IMDs to HAS often leads to task failures due to high transmission delays. UAVs with limited onboard resources require to minimize resource waste. Additionally, IMDs in sparse areas face insufficient TO services due to unfair UAV coverage. This paper defines these challenges as a joint optimization problem involving TO, RA, and UAV coverage fairness. It proposes a cooperative aerial Multiaccess Edge Computing (AMEC) framework integrating HAS and UAVs to address the issue. Within this framework, a hybrid TO scheme is first developed to mitigate the high transmission delay between IMDs and HAS. Second, a Distance, Resource, Urgency-based Decision Mechanism (DRUDM) is designed to enhance the accuracy of UAVs in selecting target IMDs for TO services. Third, a Coverage Fairness Guarantee (CFG) strategy is proposed to optimize UAV flight trajectories, ensuring IMDs in sparse areas receive fair TO services. Finally, the joint optimization problem is modeled as a Multi-Agent Partially Observable Markov Decision Process (MA-POMDP), and a DRUDM–CFG algorithm is presented to efficiently solve this complex non-convex optimization problem. Experimental results demonstrate that the proposed algorithm outperforms other compared algorithms in task completion rate and average delay, benefiting from the DRUDM mechanism. Meanwhile, the CFG strategy effectively improves TO service fairness for IMDs in sparse areas.
Xiting Peng, Chuanqi Qin, Xiaoyu Zhang et al.· IEEE Transactions on Mobile...· 4 citations
Hyperbolic surfaces are a fundamental object in mathematics and play an increasingly important role in computational geometry and topology. A key ingredient in the design of efficient algorithms on such surfaces is the availability of a geometric discretization of controlled complexity. In this paper, we present the first algorithm for constructing e-nets on hyperbolic surfaces starting from a fundamental polygon representation. Our approach is based on Delaunay refinement and relies on maintaining Delaunay triangulations through edge flips. The size of an e-net cannot be bounded solely as a function of the genus because of the presence of arbitrarily long collars around short geodesics. To overcome this difficulty, we introduce the notion of a pseudo e-net, which decomposes the surface into e-thin cylinders together with a Delaunay triangulation over an e-net of the remaining thick part. As applications, we obtain algorithms for computing the length spectrum of an e-thick hyperbolic surface and for computing the systole from a pseudo log(sqrt(2))-net. These results demonstrate that Delaunay-based discretizations provide a practical and versatile framework for algorithmic computations on hyperbolic surfaces.
V. Delecroix, Vincent Despré, Camille Lanuel et al.· 3 citations
Future 6G networks are envisaged to tightly integrate communication, sensing, and computing, demanding real-time, intent-driven intelligence at the edge. While large language models (LLMs) excel in intent recognition and semantic reasoning, their application to real-time network lifecycle management at the edge is limited by heterogeneous application intents (APPIs), dynamic network conditions, and severe resource constraints. This paper proposes a novel lightweight LLM architecture, KGLlama-KD, that synergizes knowledge graphs (KGs) with knowledge distillation (KD) to enable intent-driven networking and enhance 6G edge intelligence. Specifically, a KG is constructed to formally describe the relationships among application scenarios, functional primitives, performance requirements within APPIs, and the correspondences between APPIs and network service requests (NSRs), thereby producing a structured intent training dataset. Building upon the Llama 3 foundation model, a two-phase optimization framework is designed to support lightweight edge deployment while preserving translation fidelity. The LLM is first fine-tuned with KG guidance and compressed via KD in the cloud, and then deployed on resource-constrained edge nodes to perform real-time, accurate, and efficient APPIs interpretation. Experiments validate that KGLlama-KD achieves 95% accuracy for APPI understanding, surpassing DeepSeek and Qwen by an average of 8%. The distilled model reduces inference latency by 60% compared to full-scale LLMs, fulfilling the sub-100 ms requirement for 6G latency-sensitive services.
Bing Wu, Sai Zou, Minghui Liwang et al.· IEEE Transactions on Mobile...· 3 citations
With the rapid development of 6G and Internet of Vehicles (IoV) technologies, the volume of computation-intensive tasks generated by intelligent vehicles is growing exponentially. Given limited onboard processing capabilities, vehicles increasingly rely on edge servers deployed by service providers (SPs) at roadside units to offload tasks. Vehicle clients can offload the tasks to SPs to mitigate their onboard computation load, while SPs derive economic benefits through the provision of computation resources. However, this interaction introduces a conflict of interest, as vehicles aim to minimize their offloading costs, while SPs seek to maximize revenue. To address this problem, we propose SPOR, a Stackelberg game-based service priority-aware computation offloading and resource pricing scheme in IoV. SPOR is a hierarchical game-theoretic framework in which SPs act as leaders setting prices, while vehicles act as followers determining their offloading strategies. A novel service prioritization function is introduced, incorporating booking price, system load, and reputation to ensure fair and balanced resource allocation. We provide a theoretical proof of the existence and uniqueness of a Nash equilibrium. Extensive experiments on a real-world vehicle edge computing dataset show that SPOR outperforms baseline methods in delay, energy consumption, average load, and task completion rate. Notably, SPOR maintains task completion rates above 97% even under heavy workloads, demonstrating its effectiveness in enhancing system reliability and overall performance.
Kai Peng, Yuanlin Lin, Shuai Zhao et al.· IEEE Transactions on Mobile...· 2 citations
Blockchain-enabled mobile edge computing (MEC) must jointly optimize task offloading and consensus finality under highly heterogeneous AIoT devices, where latency/energy constraints and fairness-sensitive incentives coexist with time-varying validator reliability. We propose FE-CTDE, a unified framework that couples (1) a Stackelberg pricing-and-allocation layer that reaches a unique equilibrium and reduces utility disparity, (2) a reliability-aware dynamic BFT committee and block-packing mechanism that stabilizes confirmation delay under intermittent connectivity, and (3) a centralized-training/decentralized-execution multi-agent policy that outputs a continuous offloading ratio while requiring only local observations at run time. Extensive simulations across diverse heterogeneity, workload burstiness, and link intermittency show that FE-CTDE consistently improves social welfare and fairness while reducing end-to-end latency/energy and sustaining higher effective consensus throughput, outperforming strong baselines by up to 22.23%. We further report protocol/learning overheads and provide reproducible implementation details.
Libo Feng, Chenxi Wang, Zhenli He et al.· IEEE Transactions on Mobile...· 2 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduJul 14, 2026
Through research and entrepreneurship, Professor Devavrat Shah is helping to design methods that can handle constant decision-making using limited computational resources.
MIT News · Artificial Intelligence· news.mit.eduJun 30, 2026
Computer scientist Phillip Isola cuts through the hype to explain how AI agents work and what the future might hold for this rapidly advancing technology.
The MIT Ethics of Computing Research Symposium brought together experts and researchers working at the heart of ethical and social impact in technology.