LLM‐Assisted Design of Ultralow‐κ Chalcogenides
Yujie Liu, Congran Jia, Yuzhou Hao, Xuejie Li, Yang Wang, Artem Oganov, Jun Sun, Xiangdong Ding, Turab Lookman, Zhibin Gao · 2026
Read LLM‐Assisted Design of Ultralow‐κ Chalcogenides by Yujie Liu, Congran Jia, Yuzhou Hao, Xuejie Li, Yang Wang, Artem Oganov, Jun Sun, Xiangdong Ding, Turab Lookman, Zhibin Gao (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13672694.txt.
Description
Yujie Liu and co-authors use language models to design heat-blocking materials in this 2026 paper. Chalcogenides with very low lattice thermal conductivity suit thermoelectric devices. Finding them by first-principles search alone is slow and costly.
Their workflow lets Bayesian optimization propose candidates first. A language model then re-ranks them using evidence, before physics checks decide acceptance. Structure building, stability tests, and conductivity math form the final gate. Three silver-based compounds passed as stable finds. Their low heat flow traces to strong phonon reshaping and coherence effects. A wider screen found thousands more stable low-conductivity candidates.
Catalog record
| CREATOR | Yujie Liu, Congran Jia, Yuzhou Hao, Xuejie Li, Yang Wang, Artem Oganov, Jun Sun, Xiangdong Ding, Turab Lookman, Zhibin Gao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |