Pith. sign in

REVIEW 7 cited by

mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.03420 v2 pith:3NYXXJTO submitted 2024-09-05 cs.CV

classification cs.CV
keywords documentmulti-pageunderstandingdocowl2high-resolutionperformancetokensvisual
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multimodel Large Language Models(MLLMs) have achieved promising OCR-free Document Understanding performance by increasing the supported resolution of document images. However, this comes at the cost of generating thousands of visual tokens for a single document image, leading to excessive GPU memory and slower inference times, particularly in multi-page document comprehension. In this work, to address these challenges, we propose a High-resolution DocCompressor module to compress each high-resolution document image into 324 tokens, guided by low-resolution global visual features. With this compression module, to strengthen multi-page document comprehension ability and balance both token efficiency and question-answering performance, we develop the DocOwl2 under a three-stage training framework: Single-image Pretraining, Multi-image Continue-pretraining, and Multi-task Finetuning. DocOwl2 sets a new state-of-the-art across multi-page document understanding benchmarks and reduces first token latency by more than 50%, demonstrating advanced capabilities in multi-page questioning answering, explanation with evidence pages, and cross-page structure understanding. Additionally, compared to single-image MLLMs trained on similar data, our DocOwl2 achieves comparable single-page understanding performance with less than 20% of the visual tokens. Our codes, models, and data are publicly available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/DocOwl2.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception

    cs.CV 2026-07 conditional novelty 6.0 of 10

    BVS combines early-stop attention rollout priors with a scale-aware non-stationary kernel and GP-UCB to locate tiny objects in UHR images more accurately and with fewer MLLM queries than prior visual-search methods.

  2. Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A fine-tuning paradigm that prompts MLLMs to self-generate OCR text before translating document images improves DIMT quality and reduces catastrophic forgetting of OCR.

  3. Docopilot: Improving Multimodal Models for Document-Level Understanding

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A new academic-paper dataset and a retrieval-free fine-tuned InternVL2 model improve multi-page document QA accuracy and latency on several benchmarks.

  4. Spatially Grounded Explanations in Vision Language Models for Document Visual Question Answering

    cs.CV 2025-07 conditional novelty 5.0 of 10

    EaGERS uses a vision language model's own explanation to mask a document image to relevant grid regions, then re-asks the question, improving DocVQA accuracy while grounding answers spatially.

  5. ExpliCIT-QA: Explainable Code-Based Image Table Question Answering

    cs.CL 2025-07 conditional novelty 5.0 of 10

    ExpliCIT-QA turns table-image question answering into a traceable sequence of table extraction, natural-language reasoning, code generation, execution, and explanation.

  6. DRISHTIKON: Visual Grounding at Multiple Granularities in Documents

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A combined OCR, LLM, and fuzzy-matching pipeline locates answer spans in document images at block, line, word, and point granularity, with line-level grounding F1 of 69.10 on a new 70-document benchmark.

  7. Survey of Specialized Large Language Model

    cs.CL 2025-08 conditional novelty 2.0 of 10

    A survey of 24 specialized LLMs (2022-2025) claims a shift from domain fine-tuning to native architectures, but the synthesis is undermined by citation errors and selection bias.

Pith tools