Project team
Quickly understand what other work areas have learned, which decisions are pending and which results are already robust.
Public research and project journal
Newsroom & Research Radar
IncluLearn.AI explores how visually dominated STEM learning materials can be transformed into reviewable semantic structures and then into different accessible representations. This newsroom documents what we learn, build and still need to resolve.
Who this newsroom is for
Understand the project without reading every repository
The newsroom is designed especially for project members, the advisory board and practice partners, and the wider professional community.
Advisory board & practice partners
See where subject-matter feedback, validation and practical experience can make the greatest contribution.
Professional community
Follow research, methods and project decisions without having to read the internal repositories.
Topics
Four ways into the project
The topics are more than filters. Each one brings together its own guiding questions, focus areas and selected posts.
Project progress
Project progress
What is becoming more concrete in the project – from user needs and requirements to prototypes, evaluation, governance and services.
Research radar
Research radar
Research, standards and methods relevant to accessible STEM learning materials, semantic reconstruction and multimodal AI.
Tools & transfer
Tools & transfer
Tools, standards, open technologies and transfer questions that can turn research results into usable practice.
Publications & events
Publications & events
Our publications, talks, workshops, events and professional exchange around IncluLearn.AI.
Selected
Key starting points
These posts currently provide useful entry points to central project questions and decisions.
Project progress
Project start: IncluLearn.AI now has its own public portal
At the start of the funded project phase, the public IncluLearn.AI portal is available at inclulearn.owli-ai.com. It deliberately separates public project information, the synthetic demo and the future private pilot path.
Tools & transfer
Which open standards and tools are interesting for transfer
IncluLearn.AI does not need to reinvent every target format and transformation. MathML, EPUB Accessibility, DAISY Pipeline, Pandoc and PlantUML illustrate different building blocks for open, interoperable and reusable workflows — without implying a final tool choice.
Publications & events
PlantUML, netlists and structured text: prior work from technical education
A 2025 publication describes how visual artefacts from software engineering and technical informatics can become accessible and collaboratively editable through textual representations, including UML, electronic circuits and Karnaugh maps.
Publications & events
Five design patterns for accessible STEM learning materials
The Pattern Collection published in 2026 by Diethelm Bienhaus and Michael Kreutzer turns practical teaching experience into five reusable patterns — from text-first core content and diagrams to tactile output, sonification and human-in-the-loop explanations.
Dossiers
Preparation phase September 2026: Executive Summary
Status 23 September: before the funded project starts, requirements, research questions, the vision prototype, governance and technical foundations were prepared. This dossier summarises the main findings, open hypotheses and next steps for the project team, advisory board and practice partners.
Latest
Latest posts
Sorted by publication time. Use the archive to follow the historical project timeline.
- Research radarArticlePreparation phase
From Document AI to reviewed subject semantics
Modern Document AI models can reconstruct layout, text and scientific markup from visual documents. For IncluLearn.AI, this is an important building block — but it is not yet the subject semantics of circuits, UML, plots or other STEM artefacts.
- Research radarArticlePreparation phase
What current diagram AI can already do — and where it still fails
Recent VLM research shows progress on charts, UML and scientific diagrams. At the same time, many benchmarks measure question answering rather than complete reconstruction — a crucial distinction for accessible STEM representations.
- Research radarArticlePreparation phase
Why alt text is not enough for STEM
Technical diagrams, mathematics, circuits and quantitative graphics carry structure and relationships that often cannot be represented meaningfully in one short image description. IncluLearn.AI therefore considers structured, textual, tactile and auditory representations.
- Project progressArticlePreparation phase
Which IncluLearn.AI services could emerge from the research
From the needs hypotheses, we derived a first solution hypothesis: five core components with high strategic value, five subsequent production and integration services, and three specialised later options.