Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding

Oct-10-2025, 15:23:54 GMT–Neural Information Processing Systems

We present a novel OCR-free document understanding framework based on pre-trained Multimodal Large Language Models (MLLMs).

artificial intelligence, machine learning, natural language, (16 more...)

Neural Information Processing Systems

Oct-10-2025, 15:23:54 GMT

Conferences PDF

Country:
- Asia > South Korea > Seoul > Seoul (0.04)

Genre:
- Research Report > Experimental Study (0.93)

Industry:
- Education (1.00)
- Information Technology (0.93)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning (1.00)
    - Natural Language (1.00)
    - Vision > Image Understanding (0.66)
  - Sensing and Signal Processing > Image Processing (1.00)