TwelveLabs released Pegasus 1.6 on October 6, 2026. This video intelligence model features native egocentric video support, meaning footage captured from a first-person perspective. Targeted at robotics and physical AI teams, it automates action segmentation, detailed spatial interaction captioning, and quality control. The model can process videos up to two hours long using a 261,120-token context window. Manual annotation of this type of footage requires between 70 and 155 hours of work per hour of video, a process Pegasus 1.6 aims to replace.
Source: Read the original article
Disclaimer: this content is for information purposes only and is not financial advice. Cryptocurrencies are highly volatile: you may lose all of your capital. Always do your own research. Legal notice
