BOxCrete is an open-source AI model using Gaussian Process regression and Bayesian Optimization to predict concrete compressive strength and optimize mix designs for performance and sustainability. It addresses the complexity of modern concrete formulations by providing a reproducible, data-driven framework built on a new open-access dataset.

This paper introduces a novel hot-casted-droplet batch fabrication method for polydimethylsiloxane (PDMS) templates, designed for the robotic transfer of two-dimensional (2D) materials. The method achieves highly uniform templates with ultra-smooth surfaces and precisely controllable thermomechanical responses, crucial for advanced AI-driven material assembly.