5 papers
Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production
Yao Fehlis, Benjamin Bengfort, Zhangzhang Si +9
Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running models at production scale. To…
Exploring the Limitations of kNN Noisy Feature Detection and Recovery for Self-Driving Labs
Qiuyu Shi, Kangming Li, Yao Fehlis +4
Self-driving laboratories (SDLs) have shown promise to accelerate materials discovery by integrating machine learning with automated experimental platforms. However, errors in the…
Training-Free Active Learning Framework in Materials Science with Large Language Models
Hongchen Wang, Rafael Espinosa Castañeda, Jay R. Werber +3
Active learning (AL) accelerates scientific discovery by prioritizing the most informative experiments, but traditional machine learning (ML) models used in AL suffer from cold-sta…
When Active Learning Fails, Uncalibrated Out of Distribution Uncertainty Quantification Might Be the Problem
Ashley S. Dale, Kangming Li, Brian DeCost +4
Efficiently and meaningfully estimating prediction uncertainty is important for exploration in active learning campaigns in materials discovery, where samples with high uncertainty…
Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions
Hongchen Wang, Kangming Li, Scott Ramsay +3
Large Language Models (LLMs) have the potential to revolutionize scientific research, yet their robustness and reliability in domain-specific applications remain insufficiently exp…