Загрузка видео...

Не удалось загрузить видео

На главную

Most AI OCR tools can extract text from a document. But here's the real problem: How do you know if the extracted information is actually correct? OpenBMB just introduced something interesting with MiniCPM-OCR. It combines two specialized AI models: → MiniCPM-OCR 1.0: A compact 1.3B-parameter model that parses scanned...

AndyMarlowg's profile picture

Andy Marlow

106,387 subscribers

26,329 просмотров • 5 дней назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 16

Фото профиля czarina madueno
czarina madueno4 дней назад

This dual-model approach solves the trust issue in automation. Brilliant!

Фото профиля KJ patterson
KJ patterson4 дней назад

Game-changing architecture for reliable document AI pipelines!

Фото профиля glamrous_girl
glamrous_girl4 дней назад

Brilliant approach! Quality assurance is finally getting the AI upgrade it deserves.

Фото профиля Kelly T. Eubanks JR.
Kelly T. Eubanks JR.4 дней назад

self-checking AI workflow? Count me in!

Фото профиля Manuel si
Manuel si5 дней назад

Is it good in soanish you think ?

Фото профиля Sera Code
Sera Code5 дней назад

@grok please share more détails. whats the power of this tool ?

Фото профиля Evan Field
Evan Field5 дней назад

bro… i need to try it asap

Фото профиля Qwen AI Fans
Qwen AI Fans5 дней назад

Extraction without a second-pass check is how bad data sneaks in. Dual-model verify is the part that actually matters.

Фото профиля dobre nicolae tiberi
dobre nicolae tiberi4 дней назад

Incredible benchmarks! Open-source AI is moving at lightning speed.

Фото профиля pragyan prakash
pragyan prakash4 дней назад

Finally, an intelligent way to catch OCR errors before human review.

Фото профиля Adam
Adam5 дней назад

Powerful…

Фото профиля Adnan M.
Adnan M.5 дней назад

I will keep in mind

Фото профиля Alexa Benchmark
Alexa Benchmark5 дней назад

this is just awesome !!!

Фото профиля David Arnal
David Arnal5 дней назад

Jev’s role in flagging uncertain outputs is particularly useful; knowing when OCR needs human verification may matter more than another small gain in extraction accuracy.

Фото профиля Kayla ♔
Kayla ♔5 дней назад

its so nice !

Фото профиля OpenBMB
OpenBMB2 дней назад

Exactly! 💙 OCR is only half the story—knowing which results to trust matters just as much. Thanks for highlighting how MiniCPM-OCR and Jev work together to make document processing more reliable! 🙌

Похожие видео

Jev as a reviewer for OCR! OpenBMB and ModelBest just released MiniCPM-OCR 1.0 for document parsing and MiniCPM-OCR Jev for reviewing the reliability of those outputs. That second part is what I find more interesting. OCR errors are often hard to catch once the output looks plausible. A number can be slightly wrong, a formula can be misread, or a table cell can shift, and the result can still look completely reasonable when it moves into the next step of the workflow. MiniCPM-OCR Jev sits after the parser and evaluates how reliable those outputs are across text, formulas, and tables. It does not rewrite or correct the OCR result. Its job is to score the output and help decide which blocks can move forward and which ones should be sent for human review. So the workflow becomes: Document → Layout detection → OCR parser → Jev review → Human review where needed On the parsing side, MiniCPM-OCR 1.0 is a 1.3B model that supports scanned documents, photographed pages, curved inputs, tilted documents, tables, formulas, and key information extraction. OpenBMB reports 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, while DSpark improves end-to-end throughput by 62% in their benchmark setup. On the review side, MiniCPM-OCR Jev reaches 93.5 AUROC on their JevOCRBench, close to Qwen3.5-397B-A17B at 93.8 and above JEV-35B at 90.1 in the official evaluation. The useful part here is that you no longer have to treat the whole OCR output as equally reliable. You can review it block by block and route only the uncertain parts for another look. I tested both models on my own documents to see how well Jev catches OCR outputs that look right but are actually wrong. I’ve shared the GitHub repo below!
1:11

Jev as a reviewer for OCR! OpenBMB and ModelBest just released MiniCPM-OCR 1.0 for document parsing and MiniCPM-OCR Jev for reviewing the reliability of those outputs. That second part is what I find more interesting. OCR errors are often hard to catch once the output looks plausible. A number can be slightly wrong, a formula can be misread, or a table cell can shift, and the result can still look completely reasonable when it moves into the next step of the workflow. MiniCPM-OCR Jev sits after the parser and evaluates how reliable those outputs are across text, formulas, and tables. It does not rewrite or correct the OCR result. Its job is to score the output and help decide which blocks can move forward and which ones should be sent for human review. So the workflow becomes: Document → Layout detection → OCR parser → Jev review → Human review where needed On the parsing side, MiniCPM-OCR 1.0 is a 1.3B model that supports scanned documents, photographed pages, curved inputs, tilted documents, tables, formulas, and key information extraction. OpenBMB reports 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, while DSpark improves end-to-end throughput by 62% in their benchmark setup. On the review side, MiniCPM-OCR Jev reaches 93.5 AUROC on their JevOCRBench, close to Qwen3.5-397B-A17B at 93.8 and above JEV-35B at 90.1 in the official evaluation. The useful part here is that you no longer have to treat the whole OCR output as equally reliable. You can review it block by block and route only the uncertain parts for another look. I tested both models on my own documents to see how well Jev catches OCR outputs that look right but are actually wrong. I’ve shared the GitHub repo below!

Sumanth

21,117 просмотров • 6 дней назад

🎬 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：
1:27

🎬 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

344,220 просмотров • 7 дней назад

It's raining OCR models again! This time, OpenBMB released MiniCPM-OCR, a 1B-parameter model for document parsing I made a Hugging Face Space so you can compare its outputs against Baidu's new Unlimited OCR v2 Find the link below
0:26

It's raining OCR models again! This time, OpenBMB released MiniCPM-OCR, a 1B-parameter model for document parsing I made a Hugging Face Space so you can compare its outputs against Baidu's new Unlimited OCR v2 Find the link below

Niels Rogge

26,661 просмотров • 3 дней назад

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 OmniDocBench v1.6, Xiaomi-OCR-0 ranks first in document parsing performance among models with fewer than 1B parameters. Model weights, inference code, an interactive demo, MCP service, and Agent Skill are now open source. 👇 🤗 Huggingface: 🔗 GitHub: 📄 Demo: #XiaomiAI #OCR #OpenSource
1:06

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 OmniDocBench v1.6, Xiaomi-OCR-0 ranks first in document parsing performance among models with fewer than 1B parameters. Model weights, inference code, an interactive demo, MCP service, and Agent Skill are now open source. 👇 🤗 Huggingface: 🔗 GitHub: 📄 Demo: #XiaomiAI #OCR #OpenSource

Xiaomi Tech

150,715 просмотров • 5 дней назад

Acaban de lanzar un modelo OCR open-source de solo 1.300 millones de parámetros. Se llama MiniCPM-OCR 1.0 y viene acompañado de MiniCPM-OCR Jev, otro modelo que evalúa la fiabilidad de los resultados. Ambos desarrollados por OpenBMB y ModelBest. Entre ambos permiten: → Extraer texto, tablas y fórmulas de documentos → Procesar PDFs y páginas escaneadas o fotografiadas → Trabajar con documentos inclinados o curvados → Incluir una puntuación de confianza en los resultados para facilitar su revisión manual → Ejecutarse con vLLM, SGLang y Ollama MiniCPM-OCR 1.0 ha conseguido 93,68 puntos en Real5-OmniDocBench, según sus benchmarks oficiales. Pero lo más interesante es Jev. En lugar de corregir los errores automáticamente, evalúa la fiabilidad de los resultados extraídos e incluye una puntuación de confianza para facilitar su revisión. Además, MiniCPM-OCR 1.0 incorpora KIE (Key Information Extraction), una funcionalidad para extraer información clave de los documentos. Y sí, los pesos de ambos modelos son abiertos. 🔗 GitHub: 🤗 Hugging Face: Más recursos y demo en el primer comentario 👇
0:25

Acaban de lanzar un modelo OCR open-source de solo 1.300 millones de parámetros. Se llama MiniCPM-OCR 1.0 y viene acompañado de MiniCPM-OCR Jev, otro modelo que evalúa la fiabilidad de los resultados. Ambos desarrollados por OpenBMB y ModelBest. Entre ambos permiten: → Extraer texto, tablas y fórmulas de documentos → Procesar PDFs y páginas escaneadas o fotografiadas → Trabajar con documentos inclinados o curvados → Incluir una puntuación de confianza en los resultados para facilitar su revisión manual → Ejecutarse con vLLM, SGLang y Ollama MiniCPM-OCR 1.0 ha conseguido 93,68 puntos en Real5-OmniDocBench, según sus benchmarks oficiales. Pero lo más interesante es Jev. En lugar de corregir los errores automáticamente, evalúa la fiabilidad de los resultados extraídos e incluye una puntuación de confianza para facilitar su revisión. Además, MiniCPM-OCR 1.0 incorpora KIE (Key Information Extraction), una funcionalidad para extraer información clave de los documentos. Y sí, los pesos de ambos modelos son abiertos. 🔗 GitHub: 🤗 Hugging Face: Más recursos y demo en el primer comentario 👇

Guillermo Casaus

19,913 просмотров • 8 дней назад

A 1.2GB model on a Mac read Anthropic's whole IPO 📄 OpenBMB MiniCPM-OCR 1.0 went through all 415 pages of Anthropic's S-1 on an M5 Max MacBook at about 4 seconds a page and nothing ever left the laptop GGUFs ->
0:29

A 1.2GB model on a Mac read Anthropic's whole IPO 📄 OpenBMB MiniCPM-OCR 1.0 went through all 415 pages of Anthropic's S-1 on an M5 Max MacBook at about 4 seconds a page and nothing ever left the laptop GGUFs ->

atomic.chat

20,905 просмотров • 7 дней назад

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.
0:29

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 просмотров • 9 месяцев назад

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:
1:16

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 просмотров • 9 месяцев назад

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.
0:33

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 просмотров • 1 год назад

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→
1:21

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 просмотров • 6 месяцев назад

🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕 MiniCPM-RobotTrack — a compact model for real-world target tracking. ⚡ PhyAI — a high-performance inference framework built for embodied models. Together, they bring efficient, practical, and open embodied intelligence closer to real-world robots. ⭐ GitHub: 🤗 MiniCPM-RobotManip: 🤗 MiniCPM-RobotTrack:
1:17

🚀 MiniCPM enters the physical world — enabling robots to understand, remember, and act. We open-source MiniCPM-Robot, our first embodied AI model series, including: 🤖 MiniCPM-RobotManip — a 1.5B general-purpose Vision-Language-Action (VLA) model for robotic manipulation. 🐕 MiniCPM-RobotTrack — a compact model for real-world target tracking. ⚡ PhyAI — a high-performance inference framework built for embodied models. Together, they bring efficient, practical, and open embodied intelligence closer to real-world robots. ⭐ GitHub: 🤗 MiniCPM-RobotManip: 🤗 MiniCPM-RobotTrack:

OpenBMB

332,156 просмотров • 3 месяцев назад

💥 Introducing MiniCPM-o 2.6: An 8B size, GPT-4o level Omni Model runs on device ✨ Highlights: ~Match GPT-4o-202405 in vision, audio and multimodal live streaming ~End-to-end real-time bilingual audio conversation ~Voice cloning & emotion control ~Advanced OCR & video understanding ~Offline iPad-compatible multimodal live streaming 🔗 Try it out: GitHub: HF: Demo:
6:40

💥 Introducing MiniCPM-o 2.6: An 8B size, GPT-4o level Omni Model runs on device ✨ Highlights: ~Match GPT-4o-202405 in vision, audio and multimodal live streaming ~End-to-end real-time bilingual audio conversation ~Voice cloning & emotion control ~Advanced OCR & video understanding ~Offline iPad-compatible multimodal live streaming 🔗 Try it out: GitHub: HF: Demo:

OpenBMB

97,887 просмотров • 1 год назад

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
0:50

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 просмотров • 4 месяцев назад

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.
3:29

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 просмотров • 9 месяцев назад

We used DeepSeek OCR to extract every dataset from tables/charts across 500k+ AI arXiv papers for $1000 🚀 See which benchmarks are trending and discover datasets you didn't know existed Doing the same task with Mistral OCR would've cost $7500 👀
0:30

We used DeepSeek OCR to extract every dataset from tables/charts across 500k+ AI arXiv papers for $1000 🚀 See which benchmarks are trending and discover datasets you didn't know existed Doing the same task with Mistral OCR would've cost $7500 👀

alphaXiv

289,195 просмотров • 1 год назад

🚀 Introducing MiniCPM-V 4.5 8B: pushing the boundary of multimodal AI! ～ SOTA VL Capability: Surpasses GPT-4o, Gemini 2.0 Pro, Qwen2.5-VL 72B on OpenCompass! ～ "Eagle Eye" Video: 96x visual token compression for high refresh rate and long video understanding ～ Controllable Hybrid Fast/Deep Thinking ～ Strong OCR & Doc Parsing: Surpasses GPT-4o & Gemini 2.5 on OmniDocBench Get ready for the future of multimodal AI 👉 Huggingface｜ Github｜ Gradio｜ #AI #MiniCM #GPT #Gemini #OpenBMB #ArtificialIntelligence #MachineLearning
1:45

🚀 Introducing MiniCPM-V 4.5 8B: pushing the boundary of multimodal AI! ～ SOTA VL Capability: Surpasses GPT-4o, Gemini 2.0 Pro, Qwen2.5-VL 72B on OpenCompass! ～ "Eagle Eye" Video: 96x visual token compression for high refresh rate and long video understanding ～ Controllable Hybrid Fast/Deep Thinking ～ Strong OCR & Doc Parsing: Surpasses GPT-4o & Gemini 2.5 on OmniDocBench Get ready for the future of multimodal AI 👉 Huggingface｜ Github｜ Gradio｜ #AI #MiniCM #GPT #Gemini #OpenBMB #ArtificialIntelligence #MachineLearning

OpenBMB

25,223 просмотров • 1 год назад

India is accelerating its sovereign AI mission with homegrown models built for local languages and governance needs. Bengaluru-based Sarvam AI has launched Sarvam Vision, an OCR system for complex paper records, and Bulbul, a text-to-speech model spanning 11 Indian languages. Sarvam claims its OCR beat Google Gemini on a benchmark. Backed by government funding, the programme aims to cut dependence on foreign AI systems. Watch this report. 🔽
5:05

India is accelerating its sovereign AI mission with homegrown models built for local languages and governance needs. Bengaluru-based Sarvam AI has launched Sarvam Vision, an OCR system for complex paper records, and Bulbul, a text-to-speech model spanning 11 Indian languages. Sarvam claims its OCR beat Google Gemini on a benchmark. Backed by government funding, the programme aims to cut dependence on foreign AI systems. Watch this report. 🔽

BJP

34,446 просмотров • 8 месяцев назад

Explaining how I built an in-house mini data center to serve my entire company with massive capabilities: Image generation, image editing, vision language (OCR), text generation, coding, document processing, video generation, audio generation and soon reasoning / decision making Jev-style. Zach Vorhies chimes in on local AI vs cloud AI and why cloud AI providers are training on all our prompts.
3:04

Explaining how I built an in-house mini data center to serve my entire company with massive capabilities: Image generation, image editing, vision language (OCR), text generation, coding, document processing, video generation, audio generation and soon reasoning / decision making Jev-style. Zach Vorhies chimes in on local AI vs cloud AI and why cloud AI providers are training on all our prompts.

HealthRanger

13,608 просмотров • 1 месяц назад

Bengaluru-based startup Sarvam AI is drawing global attention with its latest AI models, Sarvam Vision and Bulbul V3. The company claims its technology has outperformed global giants like Google Gemini and ChatGPT in key optical character recognition (OCR) benchmarks. If verified, the breakthrough could mark a major moment for India’s growing AI ecosystem. What makes Sarvam Vision different? And how does Bulbul V3 push the boundaries of OCR performance? #SarvamAI
6:20

Bengaluru-based startup Sarvam AI is drawing global attention with its latest AI models, Sarvam Vision and Bulbul V3. The company claims its technology has outperformed global giants like Google Gemini and ChatGPT in key optical character recognition (OCR) benchmarks. If verified, the breakthrough could mark a major moment for India’s growing AI ecosystem. What makes Sarvam Vision different? And how does Bulbul V3 push the boundaries of OCR performance? #SarvamAI

NDTV

51,372 просмотров • 8 месяцев назад