The rapid shift of embedded intelligence in edge computing accelerates the development of autonomous systems empowered by edge AI reasoning agents, agentic AI and generative AI techniques. The workshop explores the future of this transformation, offering a critical forum to discuss the European roadmap for the next generation of edge AI systems. The presentations explore the foundational pillars of this evolution, from novel heterogeneous hardware platforms, edge AI accelerators, and bio-inspired neuromorphic architectures to the edge AI frameworks and advanced algorithms needed to power them. Key discussions will focus on the rise of Small Language Models (SLMs) optimised for embedded hardware, the deployment of Vision-Language Models (VLMs) for advanced machine perception, and the transformative potential of edge generative AI.
A central theme of the workshop is the emergence of agentic AI at the edge. We will investigate how agentic reasoning can empower individual devices and how mesh agentic AI will enable complex swarms of autonomous systems to collaborate, negotiate, and orchestrate their actions seamlessly. This leap forward is crucial for creating autonomous systems that can navigate and interact with the complexities of the real world, from innovative industry to intelligent infrastructure.
The functional requirements for edge AI systems topics address identifying and defining the core functionalities essential for deploying AI models at the edge, ensuring real-time data processing and decision-making capabilities, and exploring hardware and software design considerations for efficient AI inference at the edge.
The workshop aims to foster collaboration among academia, researchers, and industry leaders to identify and roadmap next-generation edge AI technologies and applications for secure, intelligent, and autonomous systems of the future.
The workshop combines presentations and panel discussions to allow the participants to share their insights, research findings, and best practices, facilitating a collaborative environment that promotes innovation in edge AI.
Workshop Topics
• Edge AI Trends and Technological Advancements.
• Autonomous Systems, and Swarm Intelligence.
• Agentic AI SLMs, VLMs at the Edge.
• Hardware Platforms and Accelerators Architectures.
• Synergies between edge AI and generative AI
• Optimised AI Models for Edge.
• Embedded Intelligence in Edge Computing.
• Edge AI Frameworks and Algorithms.
• European Roadmap for Edge AI.
The workshop’s concept is a holistic approach that integrates reference architectures, trustworthy frameworks, open-source collaboration, and the latest developments in SLMs optimised for embedded hardware, as well as the deployment of VLMs and edge-agentic AI.
A unique highlight of the discussion is the strategic role of open-source governance, with the workshop promoting open source as a mechanism to accelerate technology transfer and ensure European digital sovereignty.
The insights gathered form the foundation of a strategic research and innovation agenda for edge AI, a roadmap designed to strengthen European sovereignty, accelerate industrial adoption, and solidify leadership in this critical domain. This agenda aligns with parallel initiatives in AI, Data, and Robotics to build a cohesive strategy for European digital leadership.
Organizers
Ovidiu Vermesan, SINTEF, Norway.
Alain Pagani, German Research Center for Artificial Intelligence - DFKI, Germany.
Marcello Coppola, ST Microelectronics, France.
Fabian Chersi, CEA, France.