3 papers
cs.LG2025
Pre-trained knowledge elevates large language models beyond traditional chemical reaction optimizers
Robert MacKnight, Jose Emilio Regio, Jeffrey G. Ethier +2
Modern optimization in experimental chemistry employs algorithmic search through black-box parameter spaces. Here we demonstrate that pre-trained knowledge in large language models…
cs.LG2024
Modeling Multi-Step Scientific Processes with Graph Transformer Networks
Amanda A. Volk, Robert W. Epps, Jeffrey G. Ethier +1
This work presents the use of graph learning for the prediction of multi-step experimental outcomes for applications across experimental research, including material science, chemi…
cs.LG2024
Pessimistic asynchronous sampling in high-cost Bayesian optimization
Amanda A. Volk, Kristofer G. Reyes, Jeffrey G. Ethier +1
Asynchronous Bayesian optimization is a recently implemented technique that allows for parallel operation of experimental systems and disjointed workflows. Contrasting with serial…