PaLM-E

Google · March 6, 2023

activeClosedencoder decodermultimodal
Parameters562B
Context WindowN/A tokens

Description

Landmark embodied multimodal language-vision model that directly controls robotic actuators by projecting sensor inputs into language embedding space.

Key Innovations

Multimodal
MultimodalProcessing multiple types of input (text, images, audio, video) in a single model.
robotics
embodied

Family Tree

Built On

Lineage

PaLMPaLM-E

Successors (1)

More from Robotics / Embodied