AlphaSignal
2026-09-28 09:27 UTC
By AlphaSignal Newsroom
USR-0120-20260928-ai-specialis-0c43f6e9
TeleOCR Beats Gemini and GPT-5.2 at Document Parsing With 1.2B Parameters
A 1.2B open-source vision-language model unifies digital and camera-captured document parsing, topping OmniDocBench and beating larger competitors like MinerU 2.5 Pro.
A 1.2B open-source vision-language model unifies digital and camera-captured document parsing, topping OmniDocBench and beating larger competitors like MinerU 2.5 Pro.
Full article content could not be extracted automatically. Read the original below.