MatGPT: transformer-based generation of inorganic materials with targeted properties
Digital Discovery · 2026
DOI: 10.1039/d6dd00311g ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Discovery, 2026. Verfasst von Harsha Satya Vardhan Vasamsetti und 3 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0).
Abstract (Originalsprache)
MatGPT, a decoder-only transformer, generates inorganic crystals as SLICES strings. Property tokens scaled by the requested values steer generation toward target formation energy, band gap, bulk modulus and crystal system.
Zitieren
APA
Vasamsetti, H. S. V., Pal, P. K., Ehara, M., & Priyakumar, U. D. (2026). MatGPT: transformer-based generation of inorganic materials with targeted properties. Digital Discovery. https://doi.org/10.1039/d6dd00311g
Vancouver
Vasamsetti HSV, Pal PK, Ehara M, Priyakumar UD. MatGPT: transformer-based generation of inorganic materials with targeted properties. Digital Discovery. 2026. doi:10.1039/d6dd00311g
BibTeX
@article{Vasamsetti2026,
author = {Vasamsetti, Harsha Satya Vardhan and Pal, Pradeep Kumar and Ehara, Masahiro and Priyakumar, U. Deva},
title = {MatGPT: transformer-based generation of inorganic materials with targeted properties},
journal = {Digital Discovery},
year = {2026},
doi = {10.1039/d6dd00311g}
}
EUVIMED