Open Source Models

Xiaomi open-sources 0.8B Xiaomi-OCR-0, scoring 96.83 on OmniDocBench to lead sub-1B models: Xiaomi has open-sourced Xiaomi-OCR-0, a 0.8B model for document parsing, key-field extraction and OCR question answering. It scored 96.83 on OmniDocBench v1.6, ranking first among models under 1B.

AI Models • Pandaily

Nvidia's open-source Flora labels robot video for 72 cents an hour, versus $88 on GPT-6 Astra: Nvidia open-sourced Flora, a robot-video labeler built on three fine-tuned Qwen3.5 models. It labels one hour for 72 cents versus $88 with GPT-6 Astra and scores slightly higher, Nvidia says. It catches robot-action errors more reliably but sometimes falls short on descriptive accuracy.

AI & Robotics • The Decoder

Ant Group open-sources five Ming-3.0 speech models with voice design: Ant Group released five open-source Ming-3.0 speech models on October 20 covering speech synthesis, audio understanding, conversation and speech recognition. Developers can use models individually or combine them; text-to-speech supports voice cloning and natural-language voice design.

Artificial Intelligence • TechNode