We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| x-plug/mplug-docowl | canonical | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| parser_ground_line | Ran | x-plug/mplug-docowl/DocOwl1.5/evaluation/benchmarks_eval.py code served (permissive licence) · get_code("a8579cbf44eb97b3") |
| parser_line | Ran | x-plug/mplug-docowl/DocOwl1.5/evaluation/benchmarks_eval.py code served (permissive licence) · get_code("78c3cf103d2800a1") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Structure information is critical for understanding the semantics of text-rich images, such as documents, tables, and charts. Existing Multimodal Large Language Models (MLLMs) for Visual Document Understanding are equipped with text recognition ability but lack general structure understanding abilities for text-rich document images. In this work, we emphasize the importance of structure information in Visual Document Understanding and propose the Unified Structure Learning to boost the performance of MLLMs. Our Unified Structure Learning comprises structure-aware parsing tasks and multi-grained text localization tasks across 5 domains: document, webpage, table, chart, and natural image. To better encode structure information, we design a simple and effective vision-to-text module H-Reducer, which can not only maintain the layout information but also reduce the length of visual features by merging horizontal adjacent patches through convolution, enabling the LLM to understand high-resolution images more efficiently. Furthermore, by constructing structure-aware text sequences and multi-grained pairs of texts and bounding boxes for publicly available text-rich images, we build a comprehensive training set DocStruct4M to support structure learning. Finally, we construct a small but high-quality reasoning tuning dataset DocReason25K to trigger the detailed explanation ability in the document domain. Our model DocOwl 1.5 achieves state-of-the-art performance on 10 visual document understanding benchmarks, improving the SOTA performance of MLLMs with a 7B LLM by more than 10 points in 5/10 benchmarks. Our codes, models, and datasets are publicly available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/DocOwl1.5.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.12895")
get_code_for_paper("2403.12895")
have("2403.12895")
Connect an agent — have() is free.