LEAP uses a domain-specialized LLM and Bayesian optimization to prioritize perovskite additives, achieving average PCEs of 20.13% and 20.87% in later screening rounds versus 19.25% control, with a champion of 21.32%.
Perovskite-r1: a domain-specialized large language model for intelligent discovery of precursor additives and experimental design.Communications Materials, 7(86), 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LEAP: A closed-loop framework for perovskite precursor additive discovery
LEAP uses a domain-specialized LLM and Bayesian optimization to prioritize perovskite additives, achieving average PCEs of 20.13% and 20.87% in later screening rounds versus 19.25% control, with a champion of 21.32%.