正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

From recognizing text to understanding documents. 📄 Meet Xiaomi-OCR-0, an open-source document understanding model with just 0.8B parameters. It brings document parsing, key information extraction, and OCR-oriented visual question answering into one lightweight model. It scores 95.24 on Real5-OmniDocBench and 83.2 on average across five OCR-oriented VQA benchmarks. On... show more

Xiaomi Tech

4,787 subscribers

144,136 次观看 • 1 天前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

12 条评论

Pb🇮🇷 的头像

Pb🇮🇷1 天前

@grok farsi

lotus 的头像

lotus1 天前

You guys are giving closed source companies a hard time 😄😄

whiteling 的头像

whiteling1 天前

Can't OCR newspaper right.

Luke Beck 的头像

Luke Beck1 天前

Can't handle strikethrough.

علي فاضل | Ali Fadel 🥛 的头像

علي فاضل | Ali Fadel 🥛1 天前

@grok what languages are supported in this model?

Yash Patil 的头像

Yash Patil1 天前

Shipping an MCP server and an agent skill with the weights is a smart move. Most small OCR models stop at a demo, and wiring them into an agent is the annoying part. Handwritten math to LaTeX at 0.8B is impressive.

David Liu 的头像

David Liu1 天前

impressive for under 1B parameters

幽灵猎手的头像

幽灵猎手1 天前

谢谢，老实讲，和刚发布的百度的那个2.0比，谁厉害一点？

Yang Yang 的头像

Yang Yang1 天前

@grok 这个模型部署在mac studio上可以吗，需要多大内存的配置？

br 的头像

br1 天前

thanks

BaiSU 的头像

BaiSU1 天前

提高下大模型速度吧

Jimmy Young | building LUCI 的头像

Jimmy Young | building LUCI1 天前

Shipping the MCP server and agent skill with a 0.8B parser means agents can just call it locally.

相关视频

Baidu Inc. just dropped PaddleOCR-VL-1.5, and it’s not just another OCR model. This is a fully open-source OCR model with just 0.9B parameters, built specifically for production-grade document understanding. And the results speak loudly 👇 On OmniDocBench V1.5, the most authoritative global document parsing benchmark, PaddleOCR-VL-1.5 ranks #1 overall, hitting 94.5% overall accuracy, outperforming models like DeepSeek-OCR2. As the first OCR model natively supporting irregular document layout positioning, it perfectly solves OCR pain points in production for complex structured business documents such as financial reports and insurance forms. While a lot of the industry is racing toward bigger models, PaddleOCR is betting on something smarter: small parameters + high performance + open source + real usability. That combination is exactly what scalable document intelligence needs right now. Demo / API → Open source → Model → Curious to see how teams start building on top of this.

Baidu Inc. just dropped PaddleOCR-VL-1.5, and it’s not just another OCR model. This is a fully open-source OCR model with just 0.9B parameters, built specifically for production-grade document understanding. And the results speak loudly 👇 On OmniDocBench V1.5, the most authoritative global document parsing benchmark, PaddleOCR-VL-1.5 ranks #1 overall, hitting 94.5% overall accuracy, outperforming models like DeepSeek-OCR2. As the first OCR model natively supporting irregular document layout positioning, it perfectly solves OCR pain points in production for complex structured business documents such as financial reports and insurance forms. While a lot of the industry is racing toward bigger models, PaddleOCR is betting on something smarter: small parameters + high performance + open source + real usability. That combination is exactly what scalable document intelligence needs right now. Demo / API → Open source → Model → Curious to see how teams start building on top of this.

Bishal Nandi

35,318 次观看 • 9 个月前

🎬 MiniCPM-OCR in action — running locally on iPhone Duo and iPad. Parse fast and accurately. Guard the results. All in your hands. 🙌 Handwritten notes, complex formulas, newspapers, poor-quality scans—real documents put OCR to the test. 📄 MiniCPM-OCR 1.0 — SOTA OCR performance and speed at 1B scale. It achieves 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, combining accurate document parsing with efficient inference. 🛡️ MiniCPM-OCR Jev — A 2B decision model that checks OCR accuracy. It approaches Qwen3.5-397B-A17B on JevOCRBench and works with outputs from different OCR parsers. Watch it compare parsed text, formulas, and tables with the original image and assign 0–1 correctness scores—helping you pick better results and identify what needs human review. 🔓 Open weights. Deploy your way. Run with llama.cpp, vLLM, SGLang, or Ollama. Customize with open-source fine-tuning code. Watch it in action. 👇 🔗 GitHub: 🤗 Hugging Face: 👉 Try the Demo： Use the API：

🎬 MiniCPM-OCR in action — running locally on iPhone Duo and iPad. Parse fast and accurately. Guard the results. All in your hands. 🙌 Handwritten notes, complex formulas, newspapers, poor-quality scans—real documents put OCR to the test. 📄 MiniCPM-OCR 1.0 — SOTA OCR performance and speed at 1B scale. It achieves 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, combining accurate document parsing with efficient inference. 🛡️ MiniCPM-OCR Jev — A 2B decision model that checks OCR accuracy. It approaches Qwen3.5-397B-A17B on JevOCRBench and works with outputs from different OCR parsers. Watch it compare parsed text, formulas, and tables with the original image and assign 0–1 correctness scores—helping you pick better results and identify what needs human review. 🔓 Open weights. Deploy your way. Run with llama.cpp, vLLM, SGLang, or Ollama. Customize with open-source fine-tuning code. Watch it in action. 👇 🔗 GitHub: 🤗 Hugging Face: 👉 Try the Demo： Use the API：

OpenBMB

338,818 次观看 • 3 天前

Everyone is sleeping on this new OCR model! dots-ocr is a new 1.7B vision-language model that achieves SOTA performance on multilingual document parsing. - Supports 100+ languages - Works with both images and PDFs - Handles text, tables, formulas seamlessly 100% open-source.

Everyone is sleeping on this new OCR model! dots-ocr is a new 1.7B vision-language model that achieves SOTA performance on multilingual document parsing. - Supports 100+ languages - Works with both images and PDFs - Handles text, tables, formulas seamlessly 100% open-source.

Akshay 🚀

252,443 次观看 • 1 年前

i compared the top open-source OCR solutions and found which one works the best. featuring: > DeepSeek OCR > Datalab Chandra > Qwen3-VL > Dots OCR > Granite Docling also created an app that lets you run all of these OCR models in one place. 100% open-source.

i compared the top open-source OCR solutions and found which one works the best. featuring: > DeepSeek OCR > Datalab Chandra > Qwen3-VL > Dots OCR > Granite Docling also created an app that lets you run all of these OCR models in one place. 100% open-source.

Akshay 🚀

45,427 次观看 • 9 个月前

Let's talk parsing charts 📊📈. Last week we released ParseBench, the first document OCR benchmark for AI agents. New in ParseBench: ChartDataPointMatch. Most document look at a chart and OCR the caption. Agents need the actual numbers. That's the gap between "OCR'd the text around the chart" and "actually read the chart." More about ParseBench, the GitHub code, Hugging Face dataset, and scientific paper→

Let's talk parsing charts 📊📈. Last week we released ParseBench, the first document OCR benchmark for AI agents. New in ParseBench: ChartDataPointMatch. Most document look at a chart and OCR the caption. Agents need the actual numbers. That's the gap between "OCR'd the text around the chart" and "actually read the chart." More about ParseBench, the GitHub code, Hugging Face dataset, and scientific paper→

LlamaIndex 🦙

13,987 次观看 • 6 个月前

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks

The latest Qwen 3 VL by Qwen running on iPhone 17 Pro with MLX Qwen 3 VL brings upgraded visual understanding, recognition, and OCR capabilities without sacrificing text performance like previous models The 4B model here is close to Qwen 2.5 VL 72B in many benchmarks

Adrien Grondin

109,700 次观看 • 1 年前

We just released 3 million samples of high quality vision language model training dataset for use cases such as: 📄 optical character recognition (OCR) 📊 visual question answering (VQA) 📝 captioning 🤗 Learn more: 📥 Download:

We just released 3 million samples of high quality vision language model training dataset for use cases such as: 📄 optical character recognition (OCR) 📊 visual question answering (VQA) 📝 captioning 🤗 Learn more: 📥 Download:

NVIDIA AI Developer

95,858 次观看 • 1 年前

OCR can process characters but it doesn’t understand pixels. OCR has no way to reason about the headers, totals, or checkboxes found in tables, invoices, or forms. In our course with LandingAI, "Document AI: From OCR to Agentic Doc Extraction," we build agents to address these failure modes by breaking documents into pieces, applying the right tools, and mapping information to expected formats. Learn more and enroll today:

OCR can process characters but it doesn’t understand pixels. OCR has no way to reason about the headers, totals, or checkboxes found in tables, invoices, or forms. In our course with LandingAI, "Document AI: From OCR to Agentic Doc Extraction," we build agents to address these failure modes by breaking documents into pieces, applying the right tools, and mapping information to expected formats. Learn more and enroll today:

DeepLearning.AI

21,554 次观看 • 9 个月前

- <1B params - supports 91 languages - 5 pages/s on RTX 5090 - runs on CPU, GPU, MPS - 83.3% olmocr bench score (top under 3B) Surya OCR is a state-of-the-art model for document intelligence. 100% open-source.

- <1B params - supports 91 languages - 5 pages/s on RTX 5090 - runs on CPU, GPU, MPS - 83.3% olmocr bench score (top under 3B) Surya OCR is a state-of-the-art model for document intelligence. 100% open-source.

Akshay 🚀

63,902 次观看 • 5 个月前

Everyone is sleeping on this new OCR model! - 85.9% (sota) on olmocr bench - 90+ language support w/benchmarks - 4B model (down from 9B) - Full layout information - Extracts + captions images and diagrams - Strong handwriting, math, form, table support 100% open-source.

Everyone is sleeping on this new OCR model! - 85.9% (sota) on olmocr bench - 90+ language support w/benchmarks - 4B model (down from 9B) - Full layout information - Extracts + captions images and diagrams - Strong handwriting, math, form, table support 100% open-source.

Akshay 🚀

169,363 次观看 • 7 个月前

Unlimited-OCR 🔥New OCR from PaddlePaddle It can parse hundreds of pages in a single pass while maintaining stable speed. The key idea is R-SWA (Reference Sliding Window Attention), which keeps KV cache constant during decoding. 🏆 93% on OmniDocBench 📈 +6% over DeepSeek-OCR

Unlimited-OCR 🔥New OCR from PaddlePaddle It can parse hundreds of pages in a single pass while maintaining stable speed. The key idea is R-SWA (Reference Sliding Window Attention), which keeps KV cache constant during decoding. 🏆 93% on OmniDocBench 📈 +6% over DeepSeek-OCR

Adina Yakup

290,470 次观看 • 4 个月前

Check out our demos using LFM2.5-VL-3B, our latest lightweight, vision-language model that reads screens, documents, and the physical world. First up: LFM2.5-VL-3B running fully on-device in the browser with WebGPU to understand a document page. The model parses the entire layout in one pass and returns regions and labels that the interface renders as an overlay. The demo highlights OCR and layout understanding for visually structured content such as forms, reports, receipts, and other documents. 🧵

Check out our demos using LFM2.5-VL-3B, our latest lightweight, vision-language model that reads screens, documents, and the physical world. First up: LFM2.5-VL-3B running fully on-device in the browser with WebGPU to understand a document page. The model parses the entire layout in one pass and returns regions and labels that the interface renders as an overlay. The demo highlights OCR and layout understanding for visually structured content such as forms, reports, receipts, and other documents. 🧵

Liquid AI

12,613 次观看 • 2 个月前

Document OCR benchmarks are still an open problem Existing document OCR benchmarks are either too narrowly focused on a specific type (e.g. FinTabNet, ChartQA), or on documents that aren’t reflective of real-world tasks (e.g. OmniDocBench, OlmOCR-bench on over academic papers) ParseBench is a step towards solving this problem. * It tries to comprehensively cover real-world document distributions within the enterprise. * It contains comprehensive evaluations across 5 different dimensions (tables, charts, content faithfulness, formatting, grounding). * It tries to use metrics that optimize for agent semantic understanding rather than structural similarity. We released this yesterday, and there’s a TON of content: 1. Whitepaper 2. HF dataset 3. Github repo 4. Blog 5. Video And today, we’re excited to feature our home page website for ParseBench 💫 come check it out! Take a look at some of our other materials if you’re interested: Blog: Paper:

Document OCR benchmarks are still an open problem Existing document OCR benchmarks are either too narrowly focused on a specific type (e.g. FinTabNet, ChartQA), or on documents that aren’t reflective of real-world tasks (e.g. OmniDocBench, OlmOCR-bench on over academic papers) ParseBench is a step towards solving this problem. * It tries to comprehensively cover real-world document distributions within the enterprise. * It contains comprehensive evaluations across 5 different dimensions (tables, charts, content faithfulness, formatting, grounding). * It tries to use metrics that optimize for agent semantic understanding rather than structural similarity. We released this yesterday, and there’s a TON of content: 1. Whitepaper 2. HF dataset 3. Github repo 4. Blog 5. Video And today, we’re excited to feature our home page website for ParseBench 💫 come check it out! Take a look at some of our other materials if you’re interested: Blog: Paper:

Jerry Liu

21,657 次观看 • 6 个月前

Our default document parsing mode is now able to parse a complex research report with multiple embedded charts on a single page. This is the cheapest document OCR model out there that can turn complex visual documents into LLM-ready markdown. This is our agentic mode in LlamaParse. It starts at ~1c per page; if you’re looking to scale consumption we offer volume discounts. Come check it out! Sign up:

Our default document parsing mode is now able to parse a complex research report with multiple embedded charts on a single page. This is the cheapest document OCR model out there that can turn complex visual documents into LLM-ready markdown. This is our agentic mode in LlamaParse. It starts at ~1c per page; if you’re looking to scale consumption we offer volume discounts. Come check it out! Sign up:

Jerry Liu

15,479 次观看 • 9 个月前

NVIDIA drop a 3B vision-language model for fast, high-quality visual grounding in real time accurately. - Parallel box decoding - 10× faster than Qwen3-VL - Trained on 138M queries/785M boxes - GUI, OCR, and document layout, dense detection - Open source Useful for computer-use agents and Physical AI,

NVIDIA drop a 3B vision-language model for fast, high-quality visual grounding in real time accurately. - Parallel box decoding - 10× faster than Qwen3-VL - Trained on 138M queries/785M boxes - GUI, OCR, and document layout, dense detection - Open source Useful for computer-use agents and Physical AI,

Md Ismail Šojal 🕷️

133,833 次观看 • 1 个月前

Indra OCR 1.1 is out now! - 1M param main OCR model, 44 pages/s on CPU - Within 4 points of 3.4B param DeepSeek OCR 2 on OmniParseBench - 15x faster than Tesseract, and more accurate - 80+ languages, plus handwriting

Indra OCR 1.1 is out now! - 1M param main OCR model, 44 pages/s on CPU - Within 4 points of 3.4B param DeepSeek OCR 2 on OmniParseBench - 15x faster than Tesseract, and more accurate - 80+ languages, plus handwriting

Vik Paruchuri

229,692 次观看 • 12 天前

LlamaParse now has an official Agent Skill you can use across 40+ agents. With built-in instructions for parsing complex documents, including different formats, tables, charts, and images, your agents gain access to deeper document understanding, not just raw text extraction. 👇 Watch the demo 📖 Read the docs: 🚀 Get started with LlamaCloud:

LlamaParse now has an official Agent Skill you can use across 40+ agents. With built-in instructions for parsing complex documents, including different formats, tables, charts, and images, your agents gain access to deeper document understanding, not just raw text extraction. 👇 Watch the demo 📖 Read the docs: 🚀 Get started with LlamaCloud:

LlamaIndex 🦙

51,845 次观看 • 7 个月前

We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing. ✅ It contains comprehensive evals against most other major open-weight OCR models (e.g. Infinity-Parser, LightOnOCR 3, Chandra 2, dots.mocr) on multiple OCR benchmarks: ParseBench, olmOCR-bench, PulseBench-Tab, fr-bench-pdf2md. ✅ It contains detailed visibility into our data and training pipeline, to give a glimpse into how we’re able to curate the right document datasets to push the evaluation metrics within dimensions that matter for doc parsing. ✅ It is blazing fast ⚡️ decoding 2x-4x+ faster than the latest open-weight models. ✅ If you’re building your own vision models, there are 24 pages worth of appendix details (!!) that showcase all of our experimental findings from training to evals! Check it out: Other links are in our blog!

We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing. ✅ It contains comprehensive evals against most other major open-weight OCR models (e.g. Infinity-Parser, LightOnOCR 3, Chandra 2, dots.mocr) on multiple OCR benchmarks: ParseBench, olmOCR-bench, PulseBench-Tab, fr-bench-pdf2md. ✅ It contains detailed visibility into our data and training pipeline, to give a glimpse into how we’re able to curate the right document datasets to push the evaluation metrics within dimensions that matter for doc parsing. ✅ It is blazing fast ⚡️ decoding 2x-4x+ faster than the latest open-weight models. ✅ If you’re building your own vision models, there are 24 pages worth of appendix details (!!) that showcase all of our experimental findings from training to evals! Check it out: Other links are in our blog!

Jerry Liu

10,591 次观看 • 6 天前

LiteParse Samples 📄🧑‍🏫 LiteParse is our free and fast document parser that can parse text with bounding boxes from any document. I’ve created a new repository that contains some demos on how you can make use of its outputs! ✅ Comparison against PyPDF and PyMuPDF ✅ Visual Citations: search for any keyword and see joined bounding boxes pop up in the source images It should be a default tool to help AI agents OCR any document type (supports PDF, Word, Powerpoint + dozens of other formats), before heavier-weight VLM-based document parsing solutions (like our own LlamaParse). LiteParse Samples repo: LiteParse:

LiteParse Samples 📄🧑‍🏫 LiteParse is our free and fast document parser that can parse text with bounding boxes from any document. I’ve created a new repository that contains some demos on how you can make use of its outputs! ✅ Comparison against PyPDF and PyMuPDF ✅ Visual Citations: search for any keyword and see joined bounding boxes pop up in the source images It should be a default tool to help AI agents OCR any document type (supports PDF, Word, Powerpoint + dozens of other formats), before heavier-weight VLM-based document parsing solutions (like our own LlamaParse). LiteParse Samples repo: LiteParse:

Jerry Liu

13,196 次观看 • 7 个月前

Announcing: Agentic Document Extraction! PDF files represent information visually - via layout, charts, graphs, etc. - and are more than just text. Unlike traditional OCR and most PDF-to-text approaches, which focus on extracting the text, an agentic approach lets us break a document down into components and reason about them, resulting in more accurate extraction of the underlying meaning for RAG and other applications. Watch the video for details.

Announcing: Agentic Document Extraction! PDF files represent information visually - via layout, charts, graphs, etc. - and are more than just text. Unlike traditional OCR and most PDF-to-text approaches, which focus on extracting the text, an agentic approach lets us break a document down into components and reason about them, resulting in more accurate extraction of the underlying meaning for RAG and other applications. Watch the video for details.

Andrew Ng

689,842 次观看 • 1 年前