Bookmark Saya

arXiv Open Access 2026

Generative Chemical Language Models for Energetic Materials Discovery

Andrew Salij R. Seaton Ullberg Megan C. Davis Marc J. Cawkwell Christopher J. Snyder +3 lainnya
Lihat Sumber

Abstrak

The discovery of new energetic materials remains a pressing challenge hindered by limited availability of high-quality data. To address this, we have developed generative molecular language models that have been pretrained on extensive chemical data and then fine-tuned with curated energetic materials datasets. This transfer-learning strategy extends the chemical language model capabilities beyond the pharmacological space in which they have been predominantly developed, offering a framework applicable to other data-spare discovery problems. Furthermore, we discuss the benefits of fragment-based molecular encodings for chemical language models, in particular in constructing synthetically accessible structures. Together, these advances provide a foundation for accelerating the design of next-generation energetic materials with demanding performance requirements.

Topik & Kata Kunci

physics.chem-ph cond-mat.mtrl-sci cs.AI cs.CL cs.LG

Penulis (8)

A

Andrew Salij

R

R. Seaton Ullberg

M

Megan C. Davis

M

Marc J. Cawkwell

C

Christopher J. Snyder

C

Cristina Garcia Cardona

I

Ivana Matanovic

W

Wilton J. M. Kort-Kamp

Format Sitasi

APA MLA BibTeX
Salij, A., Ullberg, R.S., Davis, M.C., Cawkwell, M.J., Snyder, C.J., Cardona, C.G. et al. (2026). Generative Chemical Language Models for Energetic Materials Discovery. https://arxiv.org/abs/2604.03304

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓