4 papers
Elicitation Matters: How Prompts and Query Protocols Shape LLM Surrogates under Sparse Observations
Ge Lei, Samuel J. Cooper
Large language models are increasingly used as surrogate models for low-data optimization, but their optimizer-facing prediction and its uncertainty remain poorly understood. We st…
From Prompt to Protocol: Fast Charging Batteries with Large Language Models
Ge Lei, Ferran Brosa Planella, Sterling G. Baird +1
Efficiently optimizing battery charging protocols is challenging because each evaluation is slow, costly, and non-differentiable. Many existing approaches address this difficulty b…
evoxels: A differentiable physics framework for voxel-based microstructure simulations
Simon Daubner, Alexander E. Cohen, Benjamin Dörich +1
Materials science inherently spans disciplines: experimentalists use advanced microscopy to uncover micro- and nanoscale structure, while theorists and computational scientists dev…
Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs
Ge Lei, Samuel J. Cooper
This study explores how large language models (LLMs) encode interwoven scientific knowledge, using chemical elements and LLaMA-series models as a case study. We identify a 3D spira…