matbench

Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic Systems

Hybrid Materials Optimization System is an AI and Quantum Computing framework that compares RF, XGBoost, GB, QNN, VQR, and QKR for material property prediction. It uses Newton's Method and QAOA for optimization, ranks high-performance materials, and provides an interactive dashboard for performance comparison and recommendations.

Publication-specific scientific verification software for the Materials ML Failure Analysis research compendium.

Reproducibility package for “Decision Relevance of Uncertainty Calibration in Active-Learning Materials Screening”

Catalyst Zero Research fork of TRIADS for materials-property prediction and scientific ML workflows.

Predict ω_max (last-peak phonon frequency, cm⁻¹) for 1265 inorganic crystals on Matbench phonons. Magpie + structure/bond features + GBDT ensemble reaches MAE 34.4 cm⁻¹ on the official folds (7th of 17, ahead of CGCNN, SchNet, DimeNet++). Hand-written CGCNN included for ablation.

Materials-informatics workflow for curating hydrogel bioink formulation, rheology, and 3D-printing records, with provenance, record-linkage checks, and separate API and benchmark exercises