MinerU 4.1.6 improves PDF footnote formulas and removes duplicate nested text regions.
- Preserve formulas and formula numbers inside footnotes so they reach formula recognition and native-text filling with the correct identity.
- Remove fully contained text boxes with the same category while retaining the outer region and reading order.
- Share layout postprocessing between the ONNX and Torch backends, including formula protection and text deduplication.
- Upgrade the DocVortex dependency to
>=0.6.12,<0.7. - Add project badges to the Chinese and English documentation homepages.
Upgrade with pip install -U "mineru==4.1.6".
Full changes: mineru-4.1.5-released...mineru-4.1.6-released