← All fields

Fields

Computer vision

Recognition, detection, segmentation and video understanding

Stories: 1 · newest first

October 7, 2026

• P2 Model Unconfirmed KoreaComputer visionMultimodalRobotics & physical AI Twelve Labs
  Twelve Labs launches Pegasus 1.6, a VLM that turns first-person video into robot training data (report)

  Twelve Labs said it has launched Pegasus 1.6, a vision-language model specialized for collecting physical AI training data. It...