2 papers
cond-mat.mtrl-sci2026
Learning to Converge: Warm-Starting DFTB Self-Consistent Charges with Machine Learning
Maximilian L. Ach, Karsten Reuter, Chiara Panosetti
Semiempirical electronic structure methods such as Density-Functional Tight-Binding (DFTB) offer a computationally efficient approach to molecular and materials simulations, bridgi…
cond-mat.mtrl-sci2026
General-purpose LLMs as Constrained Crystal Composition Generators
Hedda Oschinski, Maximilian L. Ach, Konstantin S. Jakob +2
The targeted discovery of inorganic materials remains challenging due to the vastness of compositional design spaces and the high cost of exhaustive screening. Task-specific genera…