Tag
Introduces Newmark-β-DGN, a graph neural network framework that infers internal mechanical responses from coarse-step motion observations, enabling long-horizon prediction and analysis of forces without direct supervision.
This paper proposes a framework for world models in reinforcement learning by distinguishing between environment, agent, and joint system channels, using computational mechanics to define canonical predictive models and analyzing their complexity under coupling.
Introduces Physics-Audited Agentic SciML (PA-SciML), a verification-first workflow where LLM agents discover surrogate models and validate them against physics requirements such as boundary conditions and causality, not just error metrics. Numerical examples show improved trustworthiness over error-only baselines.
This paper presents a physics-informed neural network (PINN) framework for modeling transient elastodynamic wave propagation in bimaterial systems, using a steel-aluminum specimen from a Split Hopkinson Pressure Bar. The PINN accurately predicts wave transmission and reflection, validated against high-fidelity finite-element simulations, and serves as a continuous surrogate model for elastodynamic analysis.