LLM-based physics analysis agent at BESIII and exploration of future AI scientist

4 Jun 2024, 16:15
25m
Talk Machine Learning in Physics Machine learning in high energy physics

Speakers

Ke Li (Institute of High Energy Physics, China)Dr Zhengde Zhang (Institute of High Energy Physics, China)Dr Yiyu Zhang (Institute of High Energy Physics, China)

Description

The data processing and analyzing is one of the main challenges at HEP experiments, normally one physics result can take more than 3 years to be conducted. To accelerate the physics analysis and drive new physics discovery, the rapidly developing Large Language Model (LLM) is the most promising approach, it have demonstrated astonishing capabilities in recognition and generation of text while most parts of physics analysis can be benefitted. In this talk we will discuss the construction of a dedicated intelligent agent, an AI assistant at BESIII based on LLM, the potential usage to boost hadron spectroscopy study, and the future plan towards a AI scientist.

https://cern.zoom.us/j/67924643443?pwd=oHCoX0bnlWFwWq9f1AmnKa1ckQMGGB.1

Primary authors

Ke Li (Institute of High Energy Physics, China) Dr Zhengde Zhang (Institute of High Energy Physics, China) Dr Yiyu Zhang (Institute of High Energy Physics, China) Prof. Changzheng Yuan (Institute of High Energy Physics, China) Prof. Fazhi Qi (Institute of High Energy Physics, China)

Presentation Materials

Your browser is out of date!

Update your browser to view this website correctly. Update my browser now

×