Billion

This revision is from 2023/03/07 13:32. You can Restore it.

What happens when we train the largest vision-language model and add in robot experiences? The result is PaLM-E 🌴🤖, a 562-billion parameter, general-purpose, embodied visual-language generalist - across robotics, vision, and language. Website: https://palm-e.github.io - via Naval