MatterSim: Materials Modeling Workflows
During an AI for Science internship at Microsoft Research, I contributed benchmarks and computational workflows supporting materials-model development, training-data generation, and property-prediction studies.
The work involved high-throughput materials datasets, inference on models up to 1B parameters, and Azure pipelines supporting up to 10K concurrent tasks. Tools included VASP, atomate2, joblib, phonopy, phono3py, ESEN, MACE, and ORB.

Authors
AI for Science · Computational Chemistry · Computer Vision
Yu Zhu works at the intersection of AI for Science, computational chemistry,
and computer vision. His research spans machine learning force fields,
physics-driven reconstruction of molecular orbitals from scanning tunneling
microscopy images, open-set fine-grained recognition, and materials modeling.