Popular repositories Loading

1. InstructDoc InstructDoc Public

   InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions (AAAI2024)

   Python 160 6

2. SlideVQA SlideVQA Public

   SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images (AAAI2023)

   Python 88 8

3. VisualMRC VisualMRC Public

   VisualMRC: Machine Reading Comprehension on Document Images (AAAI2021)

   54

4. ToMATO ToMATO Public

   ToMATO: Verbalizing the Mental States of Role-Playing LLMs for Benchmarking Theory of Mind (AAAI2025)

   Python 10 2

5. VDocRAG VDocRAG Public

   [CVPR2025] VDocRAG: Retirval-Augmented Generation over Visually-Rich Documents

   Python 8 1