Vietnamese artificial intelligence in the world's top 12 in text recognition

The CATI-VLM model was ranked Top 12 in the world and Top 1 in Vietnam at the international Robust Reading Competition (RRC), Document Visual Question Answering (DocVQA) category, held in June 2025.

In the context of digital transformation and artificial intelligence application transformation in Vietnam taking place strongly, OCR technology (Optical Character Recognition) plays an increasingly important role in digitizing documents, automating business processes, saving costs and improving management efficiency.

However, with the characteristics of Vietnamese with accents and handwriting, the recognition problem does not stop at 'reading words', but requires the model to have the ability to understand the context comprehensively.

Faced with that challenge, CMC Technology Application Institute (CMC ATI) has developed the CATI-VLM model - a system for understanding documents using computer vision (Visual Document Understanding).

Based on a large data warehouse of up to 5TB, this model has just been ranked Top 12 in the world and Top 1 in Vietnam at the international Robust Reading Competition (RRC), Document Visual Question Answering (DocVQA) category, held in June 2025./.

(Vietnam News Agency/Vietnam+)

Source: https://www.vietnamplus.vn/tri-tue-nhan-tao-viet-vao-top-12-the-gioi-ve-nhan-dang-van-ban-post1048696.vnp