Scaling up the convolutional neural network (CNN) size (e.g., width, depth, etc.) is known to effectively improve model accuracy. However, the large model size impedes training on resource-constrained edge devices. For instance, federated learning (FL) may place undue burden on the compute capability of edge nodes, even though there is a strong practical need for FL due to its privacy and confidentiality properties. To address the resource-constrained reality of edge devices, we reformulate FL as a group knowledge transfer training algorithm, called FedGKT. FedGKT designs a variant of the alternating minimization approach to train small CNNs on edge nodes and periodically transfer their knowledge by knowledge distillation to a large server-side CNN.

Abstract--Semantic Communication (SC) combined with V e-hicular edge computing (VEC) provides an efficient edge task processing paradigm for Internet of V ehicles (IoV). Focusing on highway scenarios, this paper proposes a Tripartite Cooperative Semantic Communication (TCSC) framework, which enables V e-hicle Users (VUs) to perform semantic task offloading via V ehicle-to-Infrastructure (V2I) and V ehicle-to-V ehicle (V2V) communications. Considering task latency and the number of semantic symbols, the framework constructs a Mixed-Integer Nonlinear Programming (MINLP) problem, which is transformed into two subproblems. First, we innovatively propose a multi-agent proximal policy optimization task offloading optimization method based on parametric distribution noise (MAPPO-PDN) to solve the optimization problem of the number of semantic symbols; second, linear programming (LP) is used to solve offloading ratio. Simulations show that performance of this scheme is superior to that of other algorithms.

Static partitioning of model layers presumes temporal stability across compute and network resources, which is misaligned with the volatility of real-world deployments. We introduce a framework in which both the spatial placement and internal segmentation of foundation models are elevated to runtime-resolved constructs. The orchestration problem is formalized as a constrained optimization over layer-wise assignments, subject to evolving latency, utilization, and privacy gradients. The framework implements reactive inference composition responsive to infrastructural fluctuations by integrating model-aware capacity profiling with dynamic graph re-partitioning and reallocation. We introduce architectural and algorithmic components, along with a representative use case in 6G multi-access edge computing.

Deploying Large Language Model (LLM) services at the edge benefits latency-sensitive and privacy-aware applications. However, the stateless nature of LLMs makes managing user context (e.g., sessions, preferences) across geo-distributed edge nodes challenging. Existing solutions, such as client-side context storage, often introduce network latency and bandwidth overhead, undermining the advantages of edge deployment. We propose DisCEdge, a distributed context management system that stores and replicates user context in tokenized form across edge nodes. By maintaining context as token sequences rather than raw text, our system avoids redundant computation and enables efficient data replication. We implement and evaluate an open-source prototype in a realistic edge environment with commodity hardware. We show DisCEdge improves median response times by up to 14.46% and lowers median inter-node synchronization overhead by up to 15% compared to a raw-text-based system. It also reduces client request sizes by a median of 90% compared to client-side context management, while guaranteeing data consistency.

Large Foundation Models (LFMs), including multi-modal and generative models, promise to unlock new capabilities for next-generation Edge AI applications. However, performing inference with LFMs in resource-constrained and heterogeneous edge environments, such as Multi-access Edge Computing (MEC), presents significant challenges for workload orchestration due to time-varying network, compute, and storage conditions. In particular, current split inference strategies, which partition LFM layers across nodes, are not designed to adapt to fluctuating workloads, dynamic bandwidth conditions, or evolving privacy constraints in high-utilization MEC environments. In this work, we propose a novel adaptive split inference orchestration framework that elevates both the placement and partitioning of LFM layers to runtime-tunable variables. Specifically, our framework enables real-time, quality-of-service (QoS)-aware management of inference workloads by extending conventional orchestrators with three key services: (1) Capacity-aware workload distribution, which continuously profiles node resources and selects an optimal subset of MEC nodes; (2) Dynamic partition migration, which transparently relocates pre-cut LFM segments in response to changes in utilization or network conditions; (3) Real-time reconfiguration, which dynamically re-splits LFM layers to balance latency, throughput, and privacy. We formalize the joint placement-partitioning problem, outline a reference architecture and algorithmic workflow, and discuss applicability in representative smart city, V2X, and industrial edge scenarios.

6G networks are envisioned to support on-demand AI model downloading to accommodate diverse inference requirements of end users. By proactively caching models at edge nodes, users can retrieve the requested models with low latency for on-device AI inference. However, the substantial size of contemporary AI models poses significant challenges for edge caching under limited storage capacity, as well as for the concurrent delivery of heterogeneous models over wireless channels. To address these challenges, we propose a fine-grained AI model caching and downloading system that exploits parameter reusability, stemming from the common practice of fine-tuning task-specific models from a shared pre-trained model with frozen parameters. This system selectively caches model parameter blocks (PBs) at edge nodes, eliminating redundant storage of reusable parameters across different cached models. Additionally, it incorporates coordinated multipoint (CoMP) broadcasting to simultaneously deliver reusable PBs to multiple users, thereby enhancing downlink spectrum utilization. Under this arrangement, we formulate a model downloading delay minimization problem to jointly optimize PB caching, migration (among edge nodes), and broadcasting beamforming. To tackle this intractable problem, we develop a distributed multi-agent learning framework that enables edge nodes to explicitly learn mutual influence among their actions, thereby facilitating cooperation. Furthermore, a data augmentation approach is proposed to adaptively generate synthetic training samples through a predictive model, boosting sample efficiency and accelerating policy learning. Both theoretical analysis and simulation experiments validate the superior convergence performance of the proposed learning framework.

While simulators exist for vehicular IoT nodes communicating with the Cloud through Edge nodes in a fully-simulated osmotic architecture, they often lack support for dynamic agent planning and optimisation to minimise vehicular battery consumption while ensuring fair communication times. Addressing these challenges requires extending current simulator architectures with AI algorithms for both traffic prediction and dynamic agent planning. This paper presents an extension of SimulatorOrchestrator (SO) to meet these requirements. Preliminary results over a realistic urban dataset show that utilising vehicular planning algorithms can lead to improved battery and QoS performance compared with traditional shortest path algorithms. The additional inclusion of desirability areas enabled more ambulances to be routed to their target destinations while utilising less energy to do so, compared to traditional and weighted algorithms without desirability considerations.

We propose the Ratio1 AI meta-operating system (meta-OS), a decentralized MLOps protocol that unifies AI model development, deployment, and inference across heterogeneous edge devices. Its key innovation is an integrated blockchain-based framework that transforms idle computing resources (laptops, smartphones, cloud VMs) into a trustless global supercomputer. The architecture includes novel components: a decentralized authentication layer (dAuth), an in-memory state database (CSTORE), a distributed storage system (R1FS), homomorphic encrypted federated learning (EDIL), decentralized container orchestration (Deeploy) and an oracle network (OracleSync), which collectively ensure secure, resilient execution of AI pipelines and other container based apps at scale. The protocol enforces a formal circular token-economic model combining Proof-of-Availability (PoA) and Proof-of-AI (PoAI) consensus. Compared to centralized heterogeneous cloud MLOps and existing decentralized compute platforms, which often lack integrated AI toolchains or trusted Ratio1 node operators (R1OP) mechanics, Ratio1's holistic design lowers barriers for AI deployment and improves cost-efficiency. We provide mathematical formulations of its secure licensing and reward protocols, and include descriptive information for the system architecture and protocol flow. We argue that our proposed fully functional ecosystem proposes and demonstrates significant improvements in accessibility, scalability, and security over existing alternatives.