The accelerating shift toward intelligent, data-driven manufacturing is transforming how products are designed, produced, and optimized. To meet tight process performance targets and ambitious sustainability goals, manufacturers increasingly rely on modeling frameworks that combine predictive accuracy with computational efficiency. High-fidelity simulations and surrogate modeling techniques have emerged as critical enablers of this transition. They support a broad spectrum of applications across advanced manufacturing—from microstructural predictions in additive processes to adaptive decision-making and automation in machining, forming, and joining operations. This MS aims to engage both the classical computational mechanics and the growing scientific machine learning (SciML) communities in manufacturing by providing an inclusive platform for researchers working at the intersection of high-fidelity simulation, model order reduction, applied AI, and surrogate modeling. Contributions advancing computational methods—such as finite element and meshfree formulations, phase-field and multiphase flow models, and particle-based or discrete element methods for granular and powder systems—are especially welcome. Equally important are emerging approaches that integrate physics-based models with SciML to develop hybrid frameworks that preserve interpretability while enabling accelerated predictions essential for real-time control. Relevant topics include reduced-order modeling, physics-informed neural networks (PINNs), Bayesian surrogate modeling, uncertainty quantification (UQ), and adaptive sampling tailored to manufacturing. The symposium welcomes contributions spanning scales—from microstructural evolution and thermo-fluid/mechanical coupling to part-scale distortions and residual stresses—and materials, including metals, polymers, ceramics, and composites. It also encourages dialogue between communities focused on deterministic high-fidelity modeling and those leveraging data-driven paradigms for design space exploration, optimization, and qualification. By bringing together expertise in computational mechanics, materials science, and SciML, this MS aims to showcase methodological innovations and real-world applications that demonstrate how integrated modeling workflows can enhance process understanding, enable predictive digital twins, and accelerate the transition toward intelligent manufacturing systems.