Guidelines & Submission

Track Description:

This track invites original research contributions on Artificial Intelligence methods for diagnostic tasks performed in complex systems. Diagnostics is defined as the automated detection, identification, classification, localization, and prediction of anomalous conditions, faults, pathological states, or security threats from heterogeneous data sources.
The track emphasizes practical and implementable approaches that integrate machine learning and deep learning techniques with signal processing, sensing technologies, and embedded computing.
Contributions addressing multimodal data (images, signals, sensor streams, logs, and behavioral data) and operating in real-time or near-real-time environments are particularly encouraged.
Topics include data-driven, hybrid, and physics-based models designed to operate under conditions of uncertainty, limited supervision, noisy measurements, and domain shifts.
Applications of interest include, but are not limited to, industrial predictive maintenance, healthcare and biomedical analytics, sports performance assessment and athlete monitoring, assistive technologies, monitoring of autonomous and unmanned systems, intelligent infrastructure, and cybersecurity diagnostics.
Contributions focusing on edge computing, hardware-based artificial intelligence, reliability, explainability, and operational validation are welcome.
The goal of the program is to promote reproducible methodologies and engineering solutions that can support decision-making, improve safety, and enable proactive management strategies in engineering and science.

Track Topics:

• Fault Detection, Anomaly Detection, and Condition Monitoring
• Predictive Maintenance and Prognostics
• Medical and Biomedical Diagnostic Analytics
• Sports Performance Diagnostics and Athlete Monitoring
• Sensor-Based and Multimodal Data Diagnostics
• Edge Artificial Intelligence and Real-Time Diagnostic Systems
• Visual Perception and Biometric Recognition for Diagnostics
• Monitoring of Autonomous and Cyber-Physical Systems
• Explainable and Reliable Diagnostic Artificial Intelligence
• Dataset Creation, Validation, Benchmarking, and Deployment of AI Diagnostic Solutions

Track Brief Description - We invite submissions that address:

• Topic List

Track Brief Description - We invite submissions that address:

• Topic List

Track Brief Description - We invite submissions that address:

• Topic List

Track Description:

Digital Manufacturing encompasses the methods, tools, and technologies that enable the digital integration of design, manufacturing, inspection, and lifecycle activities within modern industrial systems. While a broad range of digital technologies contributes to this vision, CAD models increasingly play a pivotal role as structured, authoritative sources of product and process information across the digital thread. This track focuses on digital manufacturing approaches in which CAD models act as key enablers—either as central information carriers or as integrated components within larger data-driven and intelligent manufacturing ecosystems. Contributions are encouraged that explore how CAD models, when enriched with semantic, manufacturing, or quality-related information, support Model-Based Definition (MBD), interoperability, automation, and decision-making, while remaining connected to other digital manufacturing technologies. Relevant topics include the interaction between CAD models and CAx tools, digital twins, cyber-physical systems, Artificial Intelligence, and data analytics, as well as the role of standards and lightweight representations in ensuring scalable and flexible information exchange. The track welcomes both methodological contributions and industrial case studies that demonstrate how CAD-enabled digital manufacturing supports intelligent, adaptive, and reconfigurable production systems in real-world contexts.

Track Topics:

• Digital manufacturing architectures and digital thread concepts
• CAD models as enablers within digital manufacturing ecosystems
• Model-Based Definition (MBD) and Model-Based Enterprise (MBE)
• Semantic enrichment and lifecycle use of CAD models
• Integration of CAD data with AI, analytics, and decision-support systems
• Digital twins and cyber-physical systems for manufacturing
• Interoperable data formats and standards for digital manufacturing
• Plug-and-Produce and reconfigurable manufacturing systems
• Digital manufacturing for inspection, assembly, and process planning
• Industrial applications and case studies in CAD-enabled digital manufacturing

Track Description:

Recent breakthroughs in deep learning have significantly accelerated progress in computer vision, enabling models to achieve expert-level performance across various domains, including cybersecurity, healthcare, autonomous systems, and environmental monitoring. This track focuses on advancements related to the accuracy, efficiency, and explainability of visual recognition systems. With the growing deployment of computer vision models in high-stakes applications such as cybersecurity and medical imaging, transparency and reliability have become essential. As a result, the field is moving toward architectures that combine powerful feature extraction with robust explainability frameworks to ensure trustworthy decision-making.
The track welcomes contributions exploring novel neural architectures, such as Vision Transformers, hybrid CNN-Transformer models, and multimodal systems, as well as innovative training strategies, self-supervised learning paradigms, and domain adaptation methods. Emphasis is placed on explainable AI (XAI) techniques, including visualization tools, attribution methods, and model auditing strategies that help reveal the internal reasoning of modern vision systems. Additionally, the track encourages work addressing fairness, robustness, and real-world applicability, particularly in sensitive fields like medical diagnostics. By highlighting these advances, the track aims to foster interdisciplinary collaboration and support the development of computer vision systems that are not only high-performing but also interpretable, reliable, and ethically deployable.

Track Topics:

• Vision Transformers (ViT), hybrid architectures, and advanced attention mechanisms
• Explainability and interpretability methods (Grad-CAM, Attention, Rollout, CLS-based attribution, etc.)
• Deep learning for medical imaging, including ocular and non-ocular disease diagnosis
• Self-supervised, weakly supervised, and few-shot learning in vision tasks
• Domain adaptation, generalization, and transfer learning across imaging modalities
• Robustness, fairness, and bias mitigation in computer vision systems
• Multimodal and cross-modal learning (image–text, image–signal, etc.)
• Large-scale visual representation learning and foundation models
• Real-time and efficient inference methods for edge and resource-limited environments
• Benchmarking, evaluation protocols, and visual model auditing tools

Track Description:

Management of Cybersecurity and Trust is essential in any IT based architecture, application and system. Cybersecurity has to be engineered at design phase and has to be treated as a continuous and holistic process. This track welcomes submissions presenting original results on applied cybersecurity techniques, protocols and applications, especially if presented with their application and impact to real systems, software and architectures. Submissions addressing but not limited to the following topics are welcome.

Track Topics:

• Authorization and authentication mechanisms
• Trust management protocols and applications
• Innovative and Post-Quantum ready cryptography
• Trustworthy and Ethical assessment techniques also with their application to AI
• Secure Software Development (DevSecOps) and Vulnerability Identification
• Secure Communication Protocols
• Resilient System Design
• Anomaly Detection and Intrusion Detection
• Malware Dissection and Analysis

Track Brief Description - We invite submissions that address:

• Topic List

Track Description:

This session examines research at the crossroads of dynamical-systems theory, control engineering, computational reasoning, and sensory processing, with control framed as the unifying principle connecting models of biological and engineered systems across scales. We welcome work that advances theoretical foundations, such as stability, observability, and model-based control, as well as practical innovations in learning-enabled and adaptive controllers, neuro-inspired architectures for perception and decision-making, and sensorimotor integration. Contributions that develop methods for quantifying uncertainty, resilience, and collective behavior are especially encouraged.
We seek submissions that combine rigorous analytical models, data-driven inference, simulation, and experimental validation, and that highlight control principles transferable across scales. Presenters are encouraged to include reproducible evaluation frameworks and realistic deployment scenarios. Relevant topics (but not limited to) include physiological cybernetics and in-host modeling, population dynamics, adaptive control, navigation and guidance systems, and applications of artificial intelligence to biological systems. This program is aimed at researchers and practitioners pursuing rigorous, cross-disciplinary approaches to complex adaptive systems. Panel discussions will surface open challenges, efforts toward standardization, and opportunities for collaboration among theoretical researchers, experimentalists, and industry practitioners worldwide.

Track Topics:

• Physiological cybernetics and in-host modeling
• Population dynamics and multi-agent biological systems
• Navigation, guidance, and autonomous control systems
• Applications of artificial intelligence to biological and bio-inspired systems
• Dynamical-systems modeling of biological and engineered processes
• Stability, observability, and model-based control methods
• Learning-enabled and adaptive control strategies
• Neuro-inspired architectures for perception and decision-making
• Sensorimotor integration and closed-loop behavior
• Methods for quantifying uncertainty, resilience, and collective dynamics