Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
–Neural Information Processing Systems
We present a novel OCR-free document understanding framework based on pre-trained Multimodal Large Language Models (MLLMs).
Neural Information Processing Systems
Feb-17-2026, 21:43:11 GMT
- Country:
- Asia > South Korea > Seoul > Seoul (0.04)
- Genre:
- Research Report > Experimental Study (0.93)
- Industry:
- Education (1.00)
- Information Technology (0.93)
- Technology: