5th ICFA Beam Dynamics Mini-Workshop on Machine Learning for Particle Accelerators

Session

LLMs and AI Assistants

11 Apr 2025, 09:30

80/1-001 - Globe of Science and Innovation - 1st Floor (CERN)

37. Multi-modal LLMs at EuXFEL: Knowledge Assistants, Data Exploration, and Policy- 15'+5'

Florian Sohn (European XFEL GmbH)

11/04/2025, 09:30

LLMs and AI Assistants

Invited talks

Multimodal Large Language models extend LLMs’ capabilities to input beyond text, often images. At the European XFEL, these models are used as Retrieval-Augmented Generative (RAG) Knowledge assistants in technical and administrative domains. We present a selection of current applications and prototypes: chatbot assistants for data service support, business travel aid, vision-based document...

12. The Journey of Developing Specialized Text Embedding Models- 15'+5'

Thorsten Hellert

11/04/2025, 10:20

LLMs and AI Assistants

Invited talks

The specialized terminology and complex concepts inherent in physics present significant challenges for Natural Language Processing (NLP), particularly when relying on general-purpose models. In this talk, I will discuss the development of physics-specific text embedding models designed to overcome these obstacles, beginning with PhysBERT—the first model pre-trained exclusively on a curated...

9. Towards Agentic AI on Particle Accelerators- 15'+5

Raimund Kammering

11/04/2025, 10:40

LLMs and AI Assistants

Invited talks

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where...