| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| DoCoG: Mask-based Multi-Type Grounded Chain-of-Thought for Document QA | 89.4 | DoCoG (Ours) | 2026-09-08 | |
| TableMix: Enhancing Multimodal Table Reasoning in MLLMs from a Data-Centric Perspective | 88.96 | TableMix (extra data) | 2026-06-03 | |
| mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding | ✓ Link | 80.4 | DocOwl 1.5 (extra data) | 2024-03-19 |
| mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding | ✓ Link | 78.2 | DocOwl2 (extra data) | 2024-09-05 |
| M3Grounder: Mask-Based Multi-Span and Multi-Granular Grounding for Document QA | 60.4 | M3Grounder-Q | 2026-06-03 | |
| mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding | ✓ Link | 60.2 | mPLUG-DocOwl (extra data) | 2023-07-04 |