https://inclulearn-ai.github.io/newsroom/en/ Project progress, research and transfer around IncluLearn.AI. en https://inclulearn-ai.github.io/newsroom/en/news/project-start-and-public-portal/ https://inclulearn-ai.github.io/newsroom/en/news/project-start-and-public-portal/ Tue, 06 Oct 2026 10:45:00 GMT 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. project-progress https://inclulearn-ai.github.io/newsroom/en/news/which-open-standards-and-tools-matter-for-transfer/ https://inclulearn-ai.github.io/newsroom/en/news/which-open-standards-and-tools-matter-for-transfer/ Wed, 23 Sep 2026 06:31:40 GMT 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. tools-transfer https://inclulearn-ai.github.io/newsroom/en/news/plantuml-netlists-and-structured-text-in-technical-education/ https://inclulearn-ai.github.io/newsroom/en/news/plantuml-netlists-and-structured-text-in-technical-education/ Wed, 23 Sep 2026 06:31:20 GMT 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 https://inclulearn-ai.github.io/newsroom/en/news/five-design-patterns-for-accessible-stem-learning-materials/ https://inclulearn-ai.github.io/newsroom/en/news/five-design-patterns-for-accessible-stem-learning-materials/ Wed, 23 Sep 2026 06:31:00 GMT 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. publications-events https://inclulearn-ai.github.io/newsroom/en/news/from-document-ai-to-reviewed-subject-semantics/ https://inclulearn-ai.github.io/newsroom/en/news/from-document-ai-to-reviewed-subject-semantics/ Wed, 23 Sep 2026 06:13:00 GMT 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-radar https://inclulearn-ai.github.io/newsroom/en/news/what-current-diagram-ai-can-do-and-where-it-still-fails/ https://inclulearn-ai.github.io/newsroom/en/news/what-current-diagram-ai-can-do-and-where-it-still-fails/ Wed, 23 Sep 2026 06:12:00 GMT 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-radar https://inclulearn-ai.github.io/newsroom/en/news/why-alt-text-is-not-enough-for-stem/ https://inclulearn-ai.github.io/newsroom/en/news/why-alt-text-is-not-enough-for-stem/ Wed, 23 Sep 2026 06:11:00 GMT 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. research-radar https://inclulearn-ai.github.io/newsroom/en/news/which-services-could-emerge-from-the-research/ https://inclulearn-ai.github.io/newsroom/en/news/which-services-could-emerge-from-the-research/ Wed, 23 Sep 2026 05:47:00 GMT 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. project-progress https://inclulearn-ai.github.io/newsroom/en/news/twelve-needs-hypotheses-for-inclulearn-ai/ https://inclulearn-ai.github.io/newsroom/en/news/twelve-needs-hypotheses-for-inclulearn-ai/ Wed, 23 Sep 2026 05:46:00 GMT From the researched workflows, we derived twelve concrete needs hypotheses: from semantic preparation and expert review to reuse, examinations, provenance, output profiles and inclusive collaboration. project-progress https://inclulearn-ai.github.io/newsroom/en/news/what-slows-media-centres-down/ https://inclulearn-ai.github.io/newsroom/en/news/what-slows-media-centres-down/ Wed, 23 Sep 2026 05:45:00 GMT Public workflow descriptions point to high manual effort, long lead times, subject-specific transformation, established reuse practices and special examination requirements. For IncluLearn.AI, these are concrete signals of where semantic AI support may be useful. project-progress https://inclulearn-ai.github.io/newsroom/en/news/service-architecture-and-first-tts-contract-prepared/ https://inclulearn-ai.github.io/newsroom/en/news/service-architecture-and-first-tts-contract-prepared/ Tue, 22 Sep 2026 15:08:00 GMT The TTS path has moved well beyond the first September state: the engine-neutral API now runs with Qwen3-TTS-1.7B, six neutral preset profiles and VoiceDesign on the target VM and is reachable through the public test demo. This is real integration, but not yet an audio-quality or production approval. project-progress https://inclulearn-ai.github.io/newsroom/en/news/vision-prototype-and-accessible-de-en-demo-expanded/ https://inclulearn-ai.github.io/newsroom/en/news/vision-prototype-and-accessible-de-en-demo-expanded/ Tue, 22 Sep 2026 15:07:00 GMT The public prototype is not the finished AI pipeline. It is an early working model for materials, review, release and accessible use. The important foundations are user goals, accessibility-first design, DE/EN and a clear distinction between demo and real functionality. project-progress https://inclulearn-ai.github.io/newsroom/en/news/how-we-compare-models-before-deciding-on-fine-tuning/ https://inclulearn-ai.github.io/newsroom/en/news/how-we-compare-models-before-deciding-on-fine-tuning/ Tue, 22 Sep 2026 15:06:00 GMT IncluLearn.AI does not want to reduce model quality to a single benchmark. Reference data, preprocessing, structured output, rules and review paths should first be compared under the same conditions; fine-tuning remains a targeted option for clearly identified error classes. research-radar https://inclulearn-ai.github.io/newsroom/en/news/from-research-to-validated-requirements/ https://inclulearn-ai.github.io/newsroom/en/news/from-research-to-validated-requirements/ Tue, 22 Sep 2026 15:05:00 GMT Public descriptions of media-centre workflows already provide concrete evidence about effort, bottlenecks and quality requirements. IncluLearn.AI nevertheless treats the resulting needs as hypotheses until they have been validated with practice partners and users. project-progress https://inclulearn-ai.github.io/newsroom/en/news/ai-governance-and-human-review-established/ https://inclulearn-ai.github.io/newsroom/en/news/ai-governance-and-human-review-established/ Tue, 22 Sep 2026 15:04:00 GMT IncluLearn.AI deliberately separates AI involvement, subject review and approval. Human ownership, risk-based review, provenance and cautious data classification are intended to make AI useful without transferring responsibility to the system. project-progress https://inclulearn-ai.github.io/newsroom/en/news/collaboration-and-communication-channels-prepared/ https://inclulearn-ai.github.io/newsroom/en/news/collaboration-and-communication-channels-prepared/ Tue, 22 Sep 2026 15:03:00 GMT IncluLearn.AI deliberately separates open exchange, authoritative subject artefacts and public communication. The key is not the communication channel itself, but ensuring that relevant feedback can be traced into requirements, decisions, evaluation and later publications. tools-transfer https://inclulearn-ai.github.io/newsroom/en/news/reproducible-infrastructure-and-test-access-prepared/ https://inclulearn-ai.github.io/newsroom/en/news/reproducible-infrastructure-and-test-access-prepared/ Tue, 22 Sep 2026 15:02:00 GMT IncluLearn.AI's technical foundation is being built reproducibly and with clear responsibility boundaries. The public test demo can be deployed automatically, while remaining deliberately separate from later production operation with real data and stronger security requirements. project-progress https://inclulearn-ai.github.io/newsroom/en/news/project-organisation-and-working-structure-prepared/ https://inclulearn-ai.github.io/newsroom/en/news/project-organisation-and-working-structure-prepared/ Tue, 22 Sep 2026 15:01:00 GMT Before the project start, central rules for collaboration, project steering, accessibility and AI use were structured, together with a concrete start plan for the first work package. project-progress