task · first seen 15 Oct 2026
visual document understanding
Answering questions over document page images that combine text, layout, figures and tables.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Loud and Clear: Making Visual Evidence Count in Multimodal Document RAGPapers · 15 Oct 2026 · Eunchan Jo, Seounghyun Jang, Sangwoo Mo
Latest sources
- Loud and Clear: Making Visual Evidence Count in Multimodal Document RAGPapers · 15 Oct 2026 · Eunchan Jo, Seounghyun Jang, Sangwoo Mo