Welcome

The low-power edge AI for industrial applications workshop aims to bring together researchers and engineers focusing on efficient, edge AI and neuromorphic models for low-power edge platforms. It is co-located with IJCNN and will take place in Maastricht in June 2026.

Background

The widespread adoption of Artificial Intelligence (AI) in industrial environments, ranging from manufacturing and logistics to predictive maintenance and robotics, is limited by high energy and computational demands of modern neural networks. While cloud-based AI has driven major advances in perception, control and optimization, it remains unsuitable with latency-sensitive, privacy-critical and power-constrained industrial processes. The future of intelligent industry lies in edge AI: enabling low-power, adaptive and trustworthy intelligence directly to embedded and autonomous systems. The Workshop on Low-Power Edge AI for Industrial Applications (LPAI4IA) aims to gather researchers and practitioners at the intersection of efficient AI design, embedded computing, IoT and industrial deployment. It focuses on enabling advanced neural architectures, such as transformers, spiking and graph neural networks, to operate under strict energy and real-time constraints, while maintaining reliability and interpretability. Emphasis is given on cross-layer innovation, including model compression, neuromorphic computing, hardware-aware training and adaptive edge inference. Contributions addressing trustworthy and explainable AI in industrial and safety-critical scenarios are also encouraged.

Call for Papers

The workshop will cover a range of topics related to low-power edge AI, including:

• Efficient and Tiny Deep Neural Networks. Model compression, quantization, pruning, transfer learning and low-rank adaptation for energy efficiency and adaptive inference.

• Neuromorphic Systems and Spiking Neural Networks. Event-driven computation and hardware-software co-design for ultra-low-power sensing and actuation.

• Interpretable and Explainable AI / Trustworthy and Reliable AI. Transparent decision-making for safety-critical industrial operations, with cybersecurity as a particularly relevant application area.

• Federated Learning, Reinforcement Learning, Continual Learning and Cognitive Models. Self-optimizing edge systems capable of learning from evolving industrial environments.

• Neurosymbolic and Physics-inspired Neural Networks. Incorporating domain knowledge and physical constraints into compact and reliable edge models.

• Industrial Applications of Neural Networks. Deployment and validation of low-power AI in manufacturing, predictive maintenance, autonomous robotics, energy systems and process control.

• Graph Neural Networks, Transformer Networks, Mixture of Experts and Large Language Models. Efficient adaptation and distillation of large architectures for resource-constrained industrial devices.

Important dates and format

To be announced soon...

Program Committee

• Charis Kouzinopoulos - Maastricht University, Maastricht, The Netherlands

• Guangzhi Tang - Maastricht University, Maastricht, The Netherlands

• Amirreza Yousefzadeh - University of Twente, Twente, The Netherlands

• Magnus Almgren - Chalmers University of Technology, Sweden

• Georgios Keramidas - Aristotle University of Thessaloniki, Greece

Technical Program Committee

To be announced soon...

Invited speakers

To be announced soon...