
LLM, AI for science Currently at @periodiclabs, ex-xAI, ex-ByteDance, ex-MIT
- Tweets25
- Following156
- Followers122
- Likes28

ALT The rise of nanotechnology facilitates atomistically precise materials design. However, we currently lack efficient computational tools that can properly explore the gigantic design space opened up by atomic-level engineering. We develop a physics-informed neural network to design de novo atomic structures with optimum global properties and target local atomic patterns. The method significantly enhances the efficiency of evaluating atomic behaviors given structural imperfections and accelerates the design process at the meso-level. Our method pays particular attention to defects: These are abundant in solids, and vital to the macroscopic materials properties. However, a defect-property linkage typically requires significant efforts from experiments or simulations. Our graph neural network based approach achieves end-to-end translation between mesoscale crystalline structures and atom- and meso-level level properties.



















