A structure-aware graph neural network is trained to predict cross-functional energy residuals and align inconsistent DFT energy scales, which enables reliable predictions of phase stability, battery voltage profiles, and reaction thermodynamics, while allowing the integration of multi-source DFT data to advance the development of high-performance materials foundation models.
Yidong Huang, Tenglong Lu, Hanwen Kang et al.· 0 citations
This work benchmarks 23 mainstream open-source MLIPs on a low-cost NVIDIA DGX Spark, using a fixed 192-atom system under a unified ASE-based pipeline, and evaluates three dimensions: predictive accuracy, MD simulation throughput, and atomic scalability.
Hanwen Kang, Tenglong Lu, Sheng Meng et al.· 0 citations
This work releases OpenGEM26 (Open Generated Ensemble of Molecules, 2026), a large-scale dataset comprising 200,000 unique molecules and 4.4 million conformations composed of H, C, N, O, S and Cl with up to ten heavy atoms, providing a high-quality resource and robust ML potential for efficient simulations of sulfur- and chlorine-containing organic molecules.
