Materials Science
Crystals, catalysts, adsorption, materials discovery, and generative models for atomic structures.
- How periodic representations support crystal prediction and generation—and why relaxation, first-principles validation, and synthesis remain decisive.
- A material is more than a formula: discovery must connect periodic structure, competing phases, target properties, processing, and experimental formation.
- MADField predicts the full 3D adsorbate density field in nanoporous materials, turning slow gas-adsorption simulation into a single forward pass.
- How HACO, a Human–AI Co-discovery system, produced MaskGXT, a competitive generative model for crystal structure prediction.
- Gas adsorption simulation: uptake, grand canonical Monte Carlo, classical density functional theory, and density-field learning.
- Heterogeneous electrocatalysis: the energy storage problem, why oxides matter, the solid-liquid interface, and why real catalyst design is hard.