Skip to content
View guille-gil's full-sized avatar

Block or report guille-gil

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
guille-gil/README.md

Guillermo Gil de Avalle

📍 Based in Groningen, Netherlands

PhD Student in Applied AI for Industrial Maintenance | University of Groningen

University Profile ORCID LinkedIn

About

PhD student at the University of Groningen working on the Horizon Europe AIXPERT project. My research develops AI systems to assist industrial maintenance staff, combining Knowledge Graphs, RAG systems, and LLMs for procedural knowledge extraction from technical documents.

Academically focused on integration of structured knowledge into downstream tasks, in particular for industrial environments.

Research Interests

  • Knowledge Graph extraction and construction
  • LLM integration
  • Retrieval-Augmented Generation
  • Agentic workflows and tool use
  • Procedural knowledge extraction
  • Vision-Language Models and multimodal reasoning

Education

  • PhD in Applied AI (Current)
    University of Groningen, Netherlands

  • MSc Technology and Operations Management (Cum Laude)
    Data Science Specialty | Thesis on unsupervised fault detection for wind turbines
    University of Groningen, Netherlands

Experience

Previously worked as an AI Engineer / Consultant at Nexler, developing automation solutions using LLMs, APIs, and agentic frameworks, and as an Analytics Product Manager at BridgeU, developing predictive models for university admissions.

Pinned Loading

  1. aixpert-rug/FlowExtract aixpert-rug/FlowExtract Public

    Official code for "FlowExtract" (accepted: APMS 2026): A hybrid computer vision pipeline for extracting procedural knowledge graphs from industrial maintenance flowcharts.

    Python 3 1

  2. aixpert-rug/DiagFlowBench aixpert-rug/DiagFlowBench Public

    Official code for "DiagFlowBench" (accepted EMNLP 2026 Industry Track), a benchmark and dataset for evaluating how language models handle off-procedure operator inputs in flowchart-grounded industr…

    Mermaid 1