Machine learning (ML) is revolutionizing molecular dynamics (MD) simulations and opening new potential applications in mechanics. Recent advancements such as machine learning interatomic potentials (MLIPs), geometric deep learning, and generative modeling have enabled simulations of unprecedented scale, fidelity, and efficiency. This mini-symposium will provide a platform for researchers across disciplines to present and discuss cutting-edge developments at the interface of ML and molecular simulations, with an emphasis on both methodological innovations and impactful applications in mechanics, materials, and structural design.