Revolutionising Materials Science with Large Language Models: A New Paradigm in Material Discovery

Abstract:
This seminar explores the transformative potential of Large Language Models (LLMs) in revolutionising the development of advanced materials. By comparing LLMs with conventional machine learning techniques, we highlight their unique capabilities in multi-task learning, processing and generating predictions in universal formats, and leveraging vast amounts of text data to address complex questions in material development.

We propose integrating LLMs into the early stages of materials science research, enabling a paradigm shift in material recommendation and analysis. Real-world examples demonstrate how LLMs have accelerated discovery while acknowledging limitations and risks. This seminar aims to inspire researchers to embrace the potential of LLMs in materials science and foster collaboration between AI and materials science communities to unlock new frontiers in advanced materials development.

Tong Xie:
Tong Xie is a PhD candidate at the School of Photovoltaic and Renewable Energy Engineering (SPREE), UNSW Sydney, acclaimed as one of Australia’s National Computational Infrastructure’s Top 10 HPC AI-Talents. As the CEO of GreenDynamics and the Group Lead of UNSW AI4Science, he is pioneering the use of Generative AI to accelerate the discovery and development of sustainable materials. His expertise extends to Natural Language Processing and Material Science. He also founded the DARWIN natural science language model, demonstrating his innovative approach to advancing AI in material sciences.