Artificial intelligence (AI) and machine learning (ML) are revolutionizing the way researchers address longstanding challenges in contact mechanics. From data-driven modeling and enhanced simulation techniques to novel experimental analysis via advanced imaging, the integration of AI is opening new avenues for understanding and predicting contact-related phenomena across scales, materials, and applications. This mini-symposium aims to provide a broad and inclusive platform for recent advances at the intersection of contact mechanics and artificial intelligence. We welcome contributions exploring the use of AI in any aspect of contact problems, including—but not limited to—friction, wear, adhesion, roughness, tribology, and interface mechanics. Particular attention will be given to studies leveraging AI for: - Interpreting experimental images (e.g., DIC, infrared, SEM, or optical microscopy) for contact localization, damage evolution, or microstructure analysis; - Accelerating computational contact models (e.g., hybrid AI-FEM, surrogate modeling, reduced order models, Physics-Informed Neural Networks, Mixture of Experts, transformers); - Data-driven prediction of contact behaviors under complex loading and environmental conditions; - Multiscale approaches combining physical modeling and AI to bridge micro- and macro-scales; - Applications in engineering sectors such as transportation, manufacturing, energy, and bioengineering; - Prediction and health monitoring: data-driven prediction of contact behavior, early fault detection, and condition monitoring of interfaces and tribological systems - Uncertainty quantification, interpretability, and the integration of physical constraints into AI models for contact problems. We encourage submissions from both academia and industry, including original research, benchmarks, open-source tools, and methodological advances. The symposium seeks to foster interdisciplinary dialogue and highlight the diversity of AI applications in contact mechanics—paving the way for robust, interpretable, and efficient next-generation solutions.