Pith. sign in

REVIEW 12 cited by

KOSMOS-2.5: A Multimodal Literate Model

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 2309.11419 v2 pith:K6MHR2YG submitted 2023-09-20 cs.CL cs.CV

KOSMOS-2.5: A Multimodal Literate Model

classification cs.CL cs.CV
keywords kosmos-2literatetextdocumentimagesmultimodaltext-intensivebenchmarks
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The automatic reading of text-intensive images represents a significant advancement toward achieving Artificial General Intelligence (AGI). In this paper we present KOSMOS-2.5, a multimodal literate model for machine reading of text-intensive images. Pre-trained on a large-scale corpus of text-intensive images, KOSMOS-2.5 excels in two distinct yet complementary transcription tasks: (1) generating spatially-aware text blocks, where each block of text is assigned spatial coordinates within the image, and (2) producing structured text output that captures both style and structure in markdown format. This unified multimodal literate capability is achieved through a shared decoder-only autoregressive Transformer architecture and task-specific prompts. Building on this foundation, we fine-tune KOSMOS-2.5 for document understanding tasks, resulting in a document understanding generalist named KOSMOS-2.5-CHAT. Additionally, a large corpus of 357.4 million document pages spanning diverse domains was curated for pre-training. We evaluate KOSMOS-2.5 on two newly proposed benchmarks, OCREval and MarkdownEval, for document-level text recognition and image-to-markdown generation, demonstrating impressive literate capabilities comparable to GPT-4o. KOSMOS-2.5-CHAT achieves performance comparable to other state-of-the-art generalists that are five times larger (1.3B vs. 7B) across nine text-rich visual question answering benchmarks. Models and code have been available at \url{https://aka.ms/kosmos25}.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

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

  1. Towards Characterizing Scientific Image Utility and Upgradability

    cs.CV 2026-06 unverdicted novelty 7.0

    The SIU²A framework evaluates scientific images for error detection, repair feasibility, and correction quality, showing current multimodal systems have major limitations in preserving scientific validity.

  2. ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction

    cs.CV 2026-04 unverdicted novelty 7.0

    ShredBench shows state-of-the-art MLLMs perform well on intact documents but suffer sharp drops in restoration accuracy as fragmentation increases to 8-16 pieces, indicating insufficient cross-modal semantic reasoning...

  3. From Plausibility to Verifiability: Risk-Controlled Generative OCR with Vision-Language Models

    cs.CV 2026-03 unverdicted novelty 7.0

    A model-agnostic Geometric Risk Controller reduces extreme errors in VLM-based OCR by requiring cross-view consensus before accepting outputs.

  4. Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment

    cs.LG 2026-07 accept novelty 6.0

    MoE structure, not parameter count, governs INT4 robustness in sub-3B VLMs; SigLIP INT8 latency spikes on Jetson Ampere are a BitsAndBytes-Ampere interaction, and INT4 VRAM savings come with TPOT and energy penalties.

  5. MORE: A Multilingual Document Parsing Benchmark and Evaluation

    cs.CV 2026-07 conditional novelty 6.0

    MORE provides a 149-language, structure-aware document parsing benchmark from real PDFs and reports baselines showing specialized OCR models still fail on tables and rare scripts.

  6. Semantic-Guided Reading Order Reconstruction in Historical Armenian Newspapers with LLMs

    cs.CV 2026-07 unverdicted novelty 6.0

    Hybrid semantic-LLM method for reading order reconstruction in Armenian historical newspapers outperforms baselines on a new 66-page dataset while releasing a specialized Tesseract OCR model.

  7. Cross-Temporal Sinhala OCR: Page-Level Adaptation and Diachronic Analysis

    cs.CL 2026-06 unverdicted novelty 6.0

    New Sinhala OCR dataset from 1981-2019 legislative acts enables LightOnOCR-2-1B to reach 1.05% CER, beating Surya-OCR, Tesseract, and Google Document AI.

  8. CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing

    cs.CL 2026-05 unverdicted novelty 6.0

    CC-OCR V2 reveals that state-of-the-art large multimodal models substantially underperform on challenging real-world document processing tasks.

  9. Vision Language Model Helps Private Information De-Identification in Vision Data

    cs.AI 2026-06 unverdicted novelty 4.0

    VisShield with OPTIC dataset enables VLMs to localize and mask private text in vision data via instruction tuning for privacy preservation.

  10. MinerU: An Open-Source Solution for Precise Document Content Extraction

    cs.CV 2024-09 conditional novelty 4.0

    MinerU delivers an open-source pipeline for high-precision document content extraction by integrating specialized models with tuned preprocessing and postprocessing rules.

  11. How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

    cs.CV 2024-04 unverdicted novelty 4.0

    InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.

  12. A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends

    cs.CV 2025-07 unverdicted novelty 3.0

    A survey of MLLM-based Visually Rich Document Understanding covering feature integration techniques, training paradigms, challenges like data scarcity, and emerging trends such as RAG and agentic frameworks.