AI4CH-EDU 2026 Abstracts


Area 1 - AI-Assisted Authoring and Prompted Generative AI for Cultural Heritage Education

Full Papers
Paper Nr: 6
Title:

ATHENA: Archaeological Three-Dimensional Heritage Engine for Novel Artifacts

Authors:

Attilio Della Greca, Ilaria Amaro and Paola Barra

Abstract: Archaeological education has long relied on two-dimensional media to convey an inherently three-dimensional discipline, limiting students’ ability to develop an intuitive understanding of material culture. Existing digital approaches - photogrammetry, 3D scanning, and virtual heritage platforms - partially address this gap but remain dependent on physical access to artifacts or pre-authored content, and do not afford learners generative agency. This paper presents ATHENA (Archaeological Three-dimensional Heritage Engine for Novel Artifacts), a web-based educational platform that enables students and educators to create three-dimensional archaeological artifacts through two complementary AI-assisted workflows: a free-text Prompt Mode and a structured AI Wizard Mode. ATHENA integrates a two-stage generative pipeline combining diffusion-based text-to-image synthesis with single-image 3D mesh reconstruction, and delivers the resulting objects in an interactive WebGL-based viewer. By requiring learners to make explicit classificatory decisions - concerning typology, material, chronology, provenance, and conservation status - before generating an artifact, the platform transforms the act of 3D creation into a structured knowledge mobilisation exercise grounded in constructionist learning theory.
Download

Short Papers
Paper Nr: 5
Title:

From Archaeological Sources to Learning Resources: A Human-in-the-Loop Framework for AI-Assisted Authoring in Cultural Heritage Education

Authors:

Constanza Fiorella Duarte Petti, Angelo Lorusso, Michele Pellegrino, Domenico Santaniello, Pietro Giuseppe Strollo and Carmine Valentino

Abstract: Cultural heritage education increasingly relies on access to diverse digital materials, including archaeological artefacts, museum records, historical maps, and other multimodal resources. These materials are rarely available in formats directly suitable for classroom instruction. This study examines the use of multimodal generative artificial intelligence (AI) to convert such materials into structured teaching tools. Rather than conceptualising AI as an autonomous lesson-generation system, the research proposes a Human-in-the-Loop framework in which educational value emerges from the interplay of source selection, instructional design, multimodal generation, teacher critique, and iterative refinement. This approach is exemplified by a case study of the ceremonial chariot discovered at Civita Giuliana near Pompeii, which demonstrates how a complex archaeological source can be transformed into a pedagogical resource. Additionally, the paper presents a comparative analysis of various types of heritage inputs, including an archaeological object, a museum artefact record, and a historical map. The findings suggest that multimodal generative AI can substantially enhance cultural heritage instruction when integrated within a teacher-guided workflow that ensures historical accuracy, pedagogical coherence, age appropriateness, and source transparency.
Download

Paper Nr: 7
Title:

Remote Sensing and AI in Archaeology Education: A Learning Experience on Early Neolithic Ditched Villages in Southern Italy

Authors:

M. Casillo, F. Colace, A. Lorusso, M. Pellegrino, G. Strollo and C. Valentino

Abstract: This paper presents an educational experience developed for archaeology and cultural heritage students of the University of Salerno. The course translated a specialized archaeological research topic, the ditched villages of the Early Neolithic in south-eastern Italy, into a learning environment combining archaeological interpretation, remote sensing, data organization, and an introductory engagement with AI-related methods. The educational design moved progressively from theoretical framing to image interpretation and dataset construction. In this context, machine learning was introduced not as a technical skill to be directly implemented by students, but as a methodological framework guiding the preparation of data for a real clustering task. Students organized the dataset, selected relevant features, and used NotebookLM both to reflect on data preparation and to become familiar with accessible AI tools, while the clustering phase was carried out by an expert. The experience shows that digital innovation in archaeology education is most effective when computational methods are embedded in critically grounded and disciplinarily coherent learning processes.
Download