Ancient languages and AI in Archeology

Adapt state-of-the-art Visual Language Models (VLMs) for the recognition, analysis and translation of Ancient Egyptian hieroglyphic texts. This project focuses on pretraining and fine-tuning general-purpose image VLMs to develop a research assistant for Egyptology. To achieve this, we need a lot of annotated data.

Tasks:

1. Data annotation for Egyptian OCR

2. Data annotation for Egyptian assistant SFT

3. Data annotation for Egyptian translation (German-speaking only)

4. Human evaluation and RLHF fine-tuning Find collaborations for real-life applications (e.g., museums).

Other research areas:

• Automatic attribution of ceramics

• Analysis of satellite images to identify potential excavation sites

• Reconstruction of frescoes from fragments

• AI-enhanced search for analogies in historical subjects

• Unite OCR-translation-analysis pipeline for a variety of ancient languages (e.g. sumerian and persian) ​​and scripts

• The main bottleneck is the lack of specialized data on which fundamental models can be trained.

• We make extensive use of the professional expertise of domain experts to clarify the task, annotate data and evaluate the results of the model

• Our tools are designed to dramatically speed up historical research and enable scientists to make stunning new discoveries