| Date: | 19 November 2026, 13:00 – 16:00 | Price: | Free (for eligible participants) | |
| Format: | AI:AT Webinar, ONLINE (Zoom) | Target audience: | Industry, public admin, academia | |
| Language: | English | Organizer: | AI:AT |
Product development runs on technical documents. This hands-on course shows how AI can read and interpret them, from established techniques to today's multimodal models that handle the visual and textual content these documents combine.
After this course, you are able to
- Understand how AI can make the knowledge in technical documents accessible, from established techniques to multimodal models.
- Explain how multimodal models differ from text-only language models and the key ideas that make them work.
- Apply a multimodal model to interpret a technical drawing and to extract information from a specifications document.
- Assess where these approaches add value in product-development workflows and recognize their limitations.
Target audience
Everyone is welcome who wants to gain a deeper understanding of how AI can read and interpret technical documents and drawings in product development
This webinar is open and free of charge for all participants from academia, industry, and public administration from EU and/or EuroHPC JU member countries.
Entry level & prerequisites
Basic familiarity with machine learning concepts is helpful but not required. For the hands-on parts, basic Python programming is recommended.
Agenda
12:45: Zoom Meeting Opens
13:00: Welcome, Motivation & Introduction
13:15: Understanding documents and drawings with AI
- Established methods for analyzing documents
- Strengths and limitations
- Short hands-on/demonstration
13:45: Multimodal AI
- How multimodal models differ from text-only language models
- Key concepts and capabilities
- From established methods to multimodal understanding
14:15: Break
14:30: Hands-on lab: document and drawing analysis with a multimodal model
- Interpreting a technical drawing
- Extracting information
15:45: Showcase & discussion: Use Cases and limitations in product development
16:00 End of course
Speaker
Sebastian Kreuter (Fraunhofer Austria)
Sebastian Kreuter is a project manager at Fraunhofer Austria in the Intelligent Maintenance and Product Development group. He develops AI-based methods to make knowledge from texts, drawings, and other data sources accessible and usable for industrial practice. He combines recommender systems, knowledge graphs, OCR, and multimodal models to make product-development and after-sales processes more efficient and to deliberately reuse existing know-how.
Registration
Registration is required, the link to the registration form can be found on the top of this page in the menu on the left. Please register with your official institutional email address to prove your affiliation.
You will get the Zoom link in the automatic confirmation by email (subject starting with "[Indico] Registration"), please check your Spam/Junk folders). We will also send 1–2 reminders before the webinar.
Please do not hesitate to contact us at training@ai-at.eu if you have any questions.
Organizers
This webinar is organized by AI Factory Austria AI:AT.
Acknowledgements
AI Factory Austria AI:AT has received funding from the European High-Performance Computing Joint Undertaking (JU) under grant agreement No 101253078. The JU receives support from the Horizon Europe Programm of the European Union and Austria (BMIMI / FFG).