AI RESEARCH

MiAD: Mirage Atom Diffusion for De Novo Crystal Generation

arXiv CS.AI

ArXi:2511.14426v2 Announce Type: replace-cross In recent years, diffusion-based models have nstrated exceptional performance in searching for simultaneously stable, unique, and novel (S. U. N.) crystalline materials. However, most of these models don't have the ability to change the number of atoms in the crystal during the generation process, which limits the variability of model sampling trajectories. In this paper, we nstrate the severity of this restriction and