LectureRechercheRadarCadre d'investissement
Connexion / Inscription
← Retour à la lecture
ActualitésSujet · Xiaomi-OCR-0Matériel2 min de lectureRédaction DisconfirmAI

Xiaomi Open-Sources 0.8B Parameter Document Understanding Model Xiaomi-OCR-0, Claims Leading Benchmark Performance

Xiaomi has released and open-sourced Xiaomi-OCR-0, a 0.8B parameter model unifying document parsing, key information extraction, and visual question answering, reporting top scores in several benchmarks.

2026-10-31 13:43 GMT+8

Chinese technology company Xiaomi released and open-sourced its lightweight all-in-one document understanding model, Xiaomi-OCR-0, on the evening of October 30, 2026. With only 0.8 billion parameters, the model integrates three core capabilities: document parsing, Key Information Extraction (KIE), and OCR Visual Question Answering (VQA). Xiaomi states that the model is designed to tackle structured parsing challenges in complex tables, academic papers, and receipts, aiming to evolve the "Super Xiao Ai" assistant on Xiaomi phones from simple "text recognition" to deeper "document understanding."

According to Zhidongxi's report, Xiaomi-OCR-0 achieved a score of 96.83 on OmniDocBench v1.6, an authoritative benchmark for comprehensive document parsing, ranking first among models under 1B parameters. Its average score across five mainstream OCR VQA benchmarks was 83.2, outperforming models such as HunyuanOCR and TokenVL, and approaching the performance of Qwen3.5-4B with only approximately 20% of the parameter count. Additionally, on Real5-OmniDocBench, which simulates real-world physical capture conditions like curvature, reflections, and moiré patterns, the model scored 95.24, ranking first among compared models. It should be noted that these results are self-reported by the vendor and have not yet been independently reproduced.

Technically, Xiaomi-OCR-0 is built upon the Qwen3.5-0.8B-Base foundation and trained on approximately 170 million high-quality samples. The team employed a three-stage progressive strategy: first, Q-Mask text anchoring to strengthen spatial correspondence between visual features and text tokens; second, large-scale multi-task pre-training to establish a base capability for full-page parsing; and finally, mixed-task reinforcement learning to enhance complex layout restoration and multi-step reasoning. Regarding data engineering, Xiaomi introduced a heterogeneous expert consensus mechanism and a rendering-guided verification loop to filter single-model biases and correct structural defects.

Connexion / Inscription
LectureRechercheRadarCadre d'investissement

Xiaomi has fully disclosed the model weights and inference code, along with an interactive browser demo, MCP service, and Agent Skill toolkit. This move is expected to lower the barrier for integrating advanced document understanding capabilities into edge devices and AI agents, transforming OCR from a standalone tool into a callable foundational capability. For developers, access to a lightweight open-source model with strong semantic understanding capabilities may alter previous technical paths that relied on cloud-based large models or combinations of multiple specialized small models.

Sources

  • zhidx.com↗
Sujet

Xiaomi-OCR-0

小米于2026年9月底发布并开源了仅0.8B参数的文档理解模型Xiaomi-OCR-0。该模型基于Qwen3.5-0.8B基座,通过约1.7亿样本训练,统一了文档解析、关键信息抽取(KIE)与视觉问答(VQA)三项能力。在OmniDocBe…

4 étapes1 piècesMis à jour 2026-11-02 01:58

Comment on en est arrivé là

  1. 2026-09-28小米SeerRay团队在arXiv提交《Xiaomi-OCR-0 Technical Report》。arxiv.org ↗
  2. 2026-09-30Hugging Face页面显示技术报告发布,模型权重正式开源。huggingface.co ↗
  3. 2026-10-08社区贡献者prithivMLmods、xzl01等发布GGUF量化版本,ByronLeeee发布BF16 NInfer转换版。huggingface.co ↗

Ce qui reste non résolu

  • Xiaomi-OCR-0在实际手机端侧推理时的功耗与延迟表现如何?
  • 相比闭源大模型,开源轻量级模型在复杂非标准文档(如手写古籍)上的鲁棒性是否足以支撑大规模商用?
  • 小米后续是否会针对特定垂直领域(如医疗、法律)推出微调版本?
Lire le sujet complet →
Continuer la recherche →