From large-scale digitization of manuscripts and artifacts to the computational analysis of language, music, and oral traditions, Artificial Intelligence now supports multidisciplinary research across archaeology, linguistics, history, anthropology, library and archival science, museum studies, and environmental modeling. These tools enable the preservation, analysis, and interpretation of complex cultural data at scales and levels of detail previously unattainable. Within this broader landscape, AI4CHIEF focuses on leveraging AI to preserve and revitalize culture, heritage, indigenous languages, historical archives, and traditional Knowledge. Scholars are invited to submit original work to one of the thematic tracks listed below:
Track 1: AI for Cultural Heritage
Purpose:
Advance AI methods that preserve, analyze, and enrich cultural heritage—including artifacts, historical archives, art, architecture, oral histories, performance traditions, and community memory—while ensuring culturally appropriate access and interpretation.
Disciplines:
Digital Humanities; Cultural Informatics; Museum Studies; Conservation Science; Library and Archival Science; AI and Computer Science.
- Topics (including, but not limited to)
- Generative and immersive media for reconstruction and engagement;
- Culturally governed access controls
- Digitization pipelines (2D/3D scanning, photogrammetry, volumetric capture) and restoration workflows
- Computer vision for object/motif recognition and material analysis
- 3D reconstruction
- HTR/OCR for historical scripts
- Document layout analysis and degradation modeling
- Knowledge graphs, ontology alignment (e.g., heritage standards)
- Linked open data
- Generative and immersive media (AR/VR) for reconstruction and engagement
- Culturally governed access controls
Track 2: AI for Language Preservation
Purpose:
Develop AI-enabled documentation for endangered and under-documented languages, creating durable, ethically governed records for future generations.
Disciplines:
Computational Linguistics; NLP; Machine Learning; Linguistics; Education.
- Topics (including, but not limited to).
- Low-resource ASR/forced alignment;
- Speech diarization with consent;
- Self-supervised audio models
- OCR/HTR for manuscripts;
- Script normalization
- Transliteration,
- Font/encoding solutions
- Corpus creation and curation;
- Lexicon building;
- Morphological analyzers and parsers
- Data augmentation
- Archiving and preservation infrastructures
Track 3: AI for Language Revitalization
Purpose:
Co-design practical tools that promote daily use, learning, and intergenerational transmission of Indigenous languages.
Disciplines:
HCI and Human-Centered AI; Computational Linguistics; Linguistics; Learning Sciences and Educational Technology.
- Topics (including, but not limited to)
- Keyboards and input methods,
- Spell-checkers,
- Predictive text completion
- ASR/TTS and translation aids
- Conversational agents
- Tutoring systems
- Curriculum-aligned learning applications
- Handling code-switching
- Dialectal variation, and multiple orthographies
- Adapted pedagogy (classroom outcomes, learner retention, informed usage metrics)
Track 4: AI for Environmental and Climate
Purpose:
Integrate Indigenous ecological knowledge with AI for environmental monitoring, land stewardship, climate adaptation, and biodiversity protection..
Disciplines:
Environmental Science; Remote Sensing; Geospatial Analysis; Ecology and Conservation Biology; Sustainable Development; Disaster Risk Management.
- Topics (including, but not limited to)
- Satellite/airborne and in-situ sensing;
- Geospatial ML for land-cover change,
- Habitat mapping
- Cultural site monitoring
- Time-series forecasting for fire, flood and drought
- Food security; physics-informed and hybrid models
- Data fusion (optical, SAR, IoT);
- Participatory mapping and decision-support tools
- Safeguards for sensitive locations
- Assessing and reducing the environmental footprint of AI systems
Track 5: Ethical Frameworks and Data Governance
Purpose:
Establish governance and ethics-in-practice for datasets, models, and deployments that intersect with Indigenous knowledge, rights, and protocols.
Disciplines:
AI Ethics; Law and Public Policy; Indigenous Studies; Anthropology and Sociology of Science; Computer Science (Responsible AI).
- Topics (including, but not limited to):
- Indigenous data sovereignty
- Consent and benefit-sharing; culturally responsive licensing and access tiers
- Protections for Traditional Knowledge and sensitive cultural materials
- Risk assessment, harm mitigation, red-teaming for cultural contexts;
- privacy-preserving learning
- Dataset/model documentation
- Decolonizing AI design and aligning methods with Indigenous epistemologies
Track 6: AI for Community Empowerment and Sovereignty
Purpose:
Enable communities to own, govern, and sustain AI initiatives that advance self-determination across governance, education, health, language, and economic development.
Disciplines:
Indigenous Studies; Human-Centered AI; Social Sciences (digital equity, societal impact); Education (STEM and digital literacy); Public Policy (digital sovereignty).
- Topics (including, but not limited to):
- Community-driven AI development.
- Technological sovereignty for indigenous peoples.
- Co-development of AI solutions respecting indigenous rights and knowledge systems.
- AI as a tool for decolonization and revitalization.
- Empowering indigenous communities through AI.
- AI for self-determination.
- AI for intergenerational knowledge transmission.
- Development of community-controlled digital platforms and open-source tools.
- Reducing dependence on commercial platforms.
- Promoting digital literacy.
- AI for Indigenous Studies AI impacts marginalized communities
- AI for Community Empowerment and Sovereignty