@inproceedings{hassan-etal-2026-digilians-imageeval, title = "Digilians at {I}mage{E}val 2026 Shared Tasks: Modular Speech Parsing and Joint Multimodal Reasoning for {A}rabic Spoken {VQA}", author = "Hassan, Ahmed Eid and Hossam, Nour Eldeen and Rashad, Ahmed Hossam and Fawzy, Abdelrhman Mahmoud and Abdelmeguid, Mohammed Eid and Mohamed, Mohamed Hamdy", editor = "Abdul-Mageed, Muhammad and Elsayed, Tamer and Bouamor, Houda and El-Beltagy, Samhaa and Al-Khalifa, Hend and Abdelali, Ahmed and Elmadany, AbdelRahim and El Mekki, Abdellah and Darwish, Kareem and Alkhereyf, Sakhar and Luqman, Hamzah and Khalifa, Salam and Magdy, Samar and Alyafeai, Zaid and Hamed, Injy and Zaghouani, Wajdi and Zitouni, Imed", booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.96/", pages = "766--770", ISBN = "979-8-89176-497-2" }