Virtual Scientific Companion for Synchrotron Beamlines: A Prototype
Not on the map. Why?
Abstract (arXiv)
The extraordinarily high X-ray flux and specialized instrumentation at synchrotron beamlines have enabled versatile in-situ and high throughput studies that are impossible elsewhere. Dexterous and efficient control of experiments are thus crucial for efficient beamline operation. Artificial intelligence and machine learning methods are constantly being developed to enhance facility performance, but the full potential of these developments can only be reached with efficient human-computer-interaction. Natural language is the most intuitive and efficient way for humans to communicate. However, the low credibility and reproducibility of existing large language models and tools demand extensive development to be made for robust and reliable performance for scientific purposes. In this work, we introduce the prototype of virtual scientific companion (VISION) and demonstrate that it is possible to control basic beamline operations through natural language with open-source language model and the limited computational resources at beamline. The human-AI nature of VISION leverages existing automation systems and data framework at synchrotron beamlines.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 28 Dec 2023.
Builds on
16 of 37 references.
References · 16
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
- 2022Training Compute-Optimal Large Language Modelscited by 3,019
- 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
- 2016Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translationcited by 1,475
- 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
- 2022Galactica: A Large Language Model for Sciencecited by 744
4 more
- 2022The case for 4-bit precision: k-bit Inference Scaling Lawscited by 251
- 2023Opportunities for Retrieval and Tool Augmented Large Language Models in Scientific Facilitiescited by 27
- 2020Adaptive 3D convolutional neural network-based reconstruction method for 3D coherent diffraction imagingcited by 8
- 2023Domain-specific ChatBots for Science using Embeddingscited by 4
Built on by
Citing papers per year: 2024: 2.
2 papers.