Skip to content
Live
Trending storyPast story

OvisOCR3 technical report released, Xiaomi open-sources similar model

2 reports2 outlets19 days agoUpdate

The story so far

AI overview

The OvisOCR3 technical report included in Hugging Face Daily Papers states that the model is a 0.8B visual language model that unifies tasks such as document parsing, general OCR, key information extraction, image-text description, and cross-page table reconstruction through multi-mentor distillation and reinforcement learning. It scored 96.74 on OmniDocBench v1.6, ranked first in OCRBench v2 English and Chinese splits, and outperformed baseline models in multiple benchmarks. These achievements are self-reported in the report. Two days later, Xiaomi announced the open-sourcing of Xiaomi-OCR-0, another 0.8B lightweight document understanding model. Weights and inference code have been made available on Hugging Face and GitHub. The single model covers three tasks: document parsing, key information extraction, and OCR visual question answering. It also provides a browser demo, MCP service, and Agent Skill toolkit for integration.

AI-written from the reports · Updated 19 days ago

Developments

2 developments

  1. 30 Oct, 21:15 · 1 reports
    Open-source 0.8B parameter OCR small model
    ITHome · AI:Xiaomi open-sources 0.8B document understanding model Xiaomi-OCR-0, supporting Markdown and JSON output
  2. 28 Oct, 08:00 · 1 reports
    OvisOCR3 Technical Report
    Hugging Face Daily Papers:OvisOCR3 Technical Report

Coverage timeline

Follow the coverage to see every side of the story.

30 Oct
  1. ITHome · AIFeatured
    Xiaomi open-sources 0.8B document understanding model Xiaomi-OCR-0, supporting Markdown and JSON output

    Xiaomi open-sources lightweight document understanding model Xiaomi-OCR-0, with 0.8B parameter size, weights and inference code have been uploaded to Hugging Face and GitHub, a single model covers three tasks of document parsing, key information extraction, and OCR visual question answering.

28 Oct
  1. Hugging Face Daily Papers
    OvisOCR3 Technical Report

    OvisOCR3 is a 0.8B visual language model that unifies multiple OCR tasks through multi-mentor distillation and reinforcement learning, achieving SOTA results on document parsing, general OCR, key information extraction, image-text description, and cross-page table reconstruction tasks. It scored 96.74 on OmniDocBench v1.6, ranked first in OCRBench v2 English and Chinese split, and surpassed baseline models in multiple benchmark tests.