PaLI
A vision-language pretrained model proposed by Google. It jointly models images and text and can be applied to a variety of multimodal downstream tasks.
Core Facts
Timeline (last 90 days)
Google's RT-2 uses a pretrained vision-language model (such as PaLI) as the backbone to jointly encode image observations and natural language instructions, and generates discretized action tokens at the output end.
All Facts (2)
VLA directly connects pre-trained vision-language models with robot action policies, enabling robots to process natural language instructions, camera images, and low-level motion control in a unified manner.
90%UnverifiedGoogle's RT-2 uses a pretrained vision-language model (such as PaLI) as the backbone to jointly encode image observations and natural language instructions, and generates discretized action tokens at the output end.
50%