NYUAD Team Presents Multimodal Embedding Models for Arabic Hateful Memes and Unsafe Prompts
NYU Abu Dhabi researchers describe multimodal embedding models built for ArGuard shared tasks to detect Arabic hateful memes and unsafe prompts targeting generative AI.
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-11-17 05:00 · arXiv cs.CL
NYUAD at ArGuard Shared Tasks: Multimodal Embedding Models for Detecting Arabic Hateful Memes and Unsafe Prompts