Wasm: A Pipeline for Constructing Structured Arabic Interleaved Multimodal Corpora Paper • 2511.07080 • Published 17 days ago • 31
Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCR Paper • 2509.18174 • Published Sep 17 • 126
Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model Paper • 2505.17894 • Published May 23 • 221