4 papers
A closed-loop AI framework for hypothesis-driven and interpretable materials design
Kangyu Ji, Tianran Liu, Fang Sheng +3
Scientific hypothesis generation is central to materials discovery, yet current approaches often emphasize either conceptual (idea-to-data) reasoning or data-driven (data-to-idea)…
Disentangling the Effects of Simultaneous Environmental Variables on Perovskite Synthesis and Device Performance via Interpretable Machine Learning
Tianran Liu, Nicky Evans, Kangyu Ji +12
Despite the rapid rise in perovskite solar cell efficiency, poor reproducibility remains a major barrier to commercialization. Film crystallization and device performance are highl…
Multimodal transformers with elemental priors for phase classification of X-ray diffraction spectra
Kangyu Ji, Fang Sheng, Tianran Liu +2
Classifying a crystalline solid's phase using X-ray diffraction (XRD) is a challenging endeavor, first because this is a poorly constrained problem as there are nearly limitless ca…
A Self-Supervised Robotic System for Autonomous Contact-Based Spatial Mapping of Semiconductor Properties
Alexander E. Siemenn, Basita Das, Kangyu Ji +2
Integrating robotically driven contact-based material characterization techniques into self-driving laboratories can enhance measurement quality, reliability, and throughput. While…