Baidu Releases MIT-Licensed 3B OCR Model for long documents.

{
  "signal_id": "e9a20f3a-3592-48e7-b5ef-6fb6a3428dfc",
  "signal_type": "news",
  "signal_subtype": "launches",
  "detected_at": "2026-06-22T00:00:00+00:00",
  "company": {
    "name": "Baidu",
    "domain": "baidu.com"
  },
  "data": {
    "url": "https://aiweekly.co/alerts/baidu-releases-mit-licensed-3b-ocr-model-for-long-documents",
    "title": "Baidu Releases MIT-Licensed 3B OCR Model for long documents.",
    "ticker": "OTC:BAIDF",
    "excerpt": "Baidu Releases MIT-Licensed 3B OCR Model for long documents.\n\nTl;dr.\n\n* Baidu's Unlimited-OCR is a 3-billion-parameter MIT-licensed model that processes multi-page PDFs in a single inference pass.\n* The model has a 32,768-token context window and supports vLLM, SGLang, Ollama, llama.cpp, and Hugging Face Transformers.\n* No benchmark results are included in the release; training data and language coverage are also not disclosed.\n\nBaidu published Unlimited-OCR to Hugging Face, a 3-billion-parameter model for document parsing released under an MIT license. The headline capability is what the model card calls \"One-shot Long-horizon Parsing\": processing multi-page PDFs and image stacks in a single inference pass rather than requiring documents to be pre-sliced page by page. A 32,768-token context window supports that approach on longer documents.\n\nMost open-source OCR pipelines force you to cut input into individual pages, run each through a model separately, then stitch the outputs back together. The architectural bet here is that a sufficiently long context window lets the model handle that coherence itself. According to the model card, Unlimited-OCR builds on DeepSeek-OCR and DeepSeek-OCR-2, and deploys via Hugging Face Transformers, vLLM, SGLang, Docker, Ollama, and llama.cpp, meaning it should slot into most existing inference setups without significant rework.\n\nThe MIT...",
    "product": "MIT-Licensed 3B OCR Model",
    "summary": "Baidu, Inc. launches MIT-Licensed 3B OCR Model.",
    "planning": false,
    "image_url": "https://aiweekly.co/themes/custom/aiweekly/images/logo.png",
    "confidence": 0.5858,
    "product_data": {
      "full_text": "MIT-Licensed 3B OCR Model",
      "fuzzy_match": true
    },
    "published_at": "2026-06-22T00:00:00Z",
    "article_sentence": "Baidu Releases MIT-Licensed 3B OCR Model for long documents."
  }
}

curl https://signals.autobound.ai/v1/signals/e9a20f3a-3592-48e7-b5ef-6fb6a3428dfc \
  -H "X-API-KEY: $AUTOBOUND_API_KEY"

curl -X POST https://signals.autobound.ai/v1/companies/enrich \
  -H "X-API-KEY: $AUTOBOUND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"domain":"baidu.com","limit":20}'