Saved in:
Bibliographic Details
Main Authors: Mathur, Shray, van der Vleuten, Noah, Yager, Kevin, Tsai, Esther
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.18161
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916850719260672
author Mathur, Shray
van der Vleuten, Noah
Yager, Kevin
Tsai, Esther
author_facet Mathur, Shray
van der Vleuten, Noah
Yager, Kevin
Tsai, Esther
contents Scientific user facilities, such as synchrotron beamlines, are equipped with a wide array of hardware and software tools that require a codebase for human-computer-interaction. This often necessitates developers to be involved to establish connection between users/researchers and the complex instrumentation. The advent of generative AI presents an opportunity to bridge this knowledge gap, enabling seamless communication and efficient experimental workflows. Here we present a modular architecture for the Virtual Scientific Companion (VISION) by assembling multiple AI-enabled cognitive blocks that each scaffolds large language models (LLMs) for a specialized task. With VISION, we performed LLM-based operation on the beamline workstation with low latency and demonstrated the first voice-controlled experiment at an X-ray scattering beamline. The modular and scalable architecture allows for easy adaptation to new instrument and capabilities. Development on natural language-based scientific experimentation is a building block for an impending future where a science exocortex -- a synthetic extension to the cognition of scientists -- may radically transform scientific practice and discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18161
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VISION: A Modular AI Assistant for Natural Human-Instrument Interaction at Scientific User Facilities
Mathur, Shray
van der Vleuten, Noah
Yager, Kevin
Tsai, Esther
Artificial Intelligence
Scientific user facilities, such as synchrotron beamlines, are equipped with a wide array of hardware and software tools that require a codebase for human-computer-interaction. This often necessitates developers to be involved to establish connection between users/researchers and the complex instrumentation. The advent of generative AI presents an opportunity to bridge this knowledge gap, enabling seamless communication and efficient experimental workflows. Here we present a modular architecture for the Virtual Scientific Companion (VISION) by assembling multiple AI-enabled cognitive blocks that each scaffolds large language models (LLMs) for a specialized task. With VISION, we performed LLM-based operation on the beamline workstation with low latency and demonstrated the first voice-controlled experiment at an X-ray scattering beamline. The modular and scalable architecture allows for easy adaptation to new instrument and capabilities. Development on natural language-based scientific experimentation is a building block for an impending future where a science exocortex -- a synthetic extension to the cognition of scientists -- may radically transform scientific practice and discovery.
title VISION: A Modular AI Assistant for Natural Human-Instrument Interaction at Scientific User Facilities
topic Artificial Intelligence
url https://arxiv.org/abs/2412.18161