Xiaomi has open-sourced an 800 million-parameter OCR model that can read complex tables, extract information, and answer questions.
2026.10.31 10:09:18
Beating AI Insight News Brief: Xiaomi has open-sourced Xiaomi-OCR-0, an 800-million-parameter model capable of three core tasks: converting text, complex tables, and mathematical formulas in documents into editable content; extracting specified fields from invoices, receipts, and certificates and outputting them in JSON format; and answering questions based on document and chart information, going beyond basic image text transcription. The model is fine-tuned on Alibaba’s Qwen3.5-0.8B, trained with roughly 170 million OCR and document understanding samples. To enhance data quality, Xiaomi had multiple OCR models cross-verify recognition results. For complex tables and formulas, the team re-renders recognition outputs into images and compares them with originals to catch issues like misalignment and missing characters. Training was conducted in phases: first mastering text recognition and layout parsing, then adding tasks including information extraction and visual question answering (VQA). In five OCR VQA tests released by Xiaomi, Xiaomi-OCR-0 notched an average score of 83.2, outperforming Qwen3.5-2B (80.9) — a model with 2.5 times more parameters — and approaching the 84.9 score of the 4B-parameter model. In the Real5 document parsing test, which simulates interferences such as scanning artifacts, paper warping, and screen photo capture, the model scored 95.24 when paired with an external layout detector. Currently, the model weights, inference code, MCP service, and Agent Skill are all open-sourced. Developers can integrate Xiaomi-OCR-0 into AI Agents to process screenshots, PDFs, and invoices, extracting data that can be directly processed by other applications.
US and South Korean stock pre-market preview for Monday: SK Hynix is projected to open around 5.2% lower, while most US stocks are gaining in pre-market trading.
3 hours ago
Jefferies upgrades SpaceX rating to Buy, sets $210 target price.
3 hours ago
US Treasury Secretary Scott Bessent: Market sell-offs stem from factors including Federal Reserve remarks, midterm elections and other factors.
3 hours ago
Cysic CEO: Public keys of addresses holding over 6 million Bitcoin have been made public on-chain.
3 hours ago
Ansem: Remains bearish on Bitcoin until it rebounds above $82,500
3 hours ago
A crypto whale has built up positions of 2.565 trillion PEPE tokens over the past five days, valued at approximately $9.41 million.
3 hours ago
Hot feeds
A trader profits $448K by monitoring #Binance's new listings!
2024.12.13 17:37:29
Last week, funds have flowed into #Bitcoin, #Ethereum, and #Hyperliquid.
2024.12.16 14:48:36
A $PEPE whale that had been dormant for 600 days transferred all 2.1T $PEPE($52M) to a new address.
2024.12.14 10:35:27
NFT project Ptah has launched, with its trading volume exceeding $900,000 in just half a day; its minting mechanism mandates the use of a Binance Agent ID.
2026.10.23 10:16:30
When Elon Musk tweeted about Moltbook, the meme coin MOLT experienced a short-term 30% price surge, hitting a new all-time high of $114 million.
2026.01.31 18:37:29
A smart #AI coin trader made $17.6M on $GOAT, $ai16z, $Fartcoin,$arc.
2025.01.05 16:05:18
MoreHot Articles

How did I turn $1,000 into $30,000 with smart money?
2024.12.09

10 promising AI Agent cryptos
2024.12.05

The 30-Year-Old Entrepreneur Behind Virtual, a Multi-Million Dollar AI Agent Society
2025.01.22

10 smart traders specializing in MEMEcoin trading on Solana
2024.12.09

A trader lost $73.9K trading memecoins in just 3 minutes — a lesson for us all!
2024.12.13

What is $SPORE? Let us take you through the on-chain records to show you how it works.
2024.12.25

