cd/entity/HATFormer· home› entities› HATFormer
grep -l @hatformer /news/*.json | wc -l → 1

HATFormer

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

10:50
2026-08-18
discuss.huggingface.co
artificial-intelligence

FIne-tuned Qwen2.5-VL-3B for Arabic historical manuscript

Researchers at CERIST in Algeria released a fine-tuned Qwen2.5-VL-3B model for Arabic historical manuscript recognition, achieving a 6.58% character error rate and 22.34% word error rate. The model, a…

// co-occurs with top 6 entities
CERIST 1 Qwen2.5-VL-3B 1 Hugging Face 1 Belgacem123 1 Muharaf 1 NAKBA 2026 1
// topics top 5 topics
artificial intelligence 1 machine learning 1 large language models 1 computer vision 1 ai research 1