DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
Paper
•
2411.02359
•
Published
•
13
This repository contains the models of the paper DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution.
The models are based on the following open-sourced models:
Base model
openflamingo/OpenFlamingo-3B-vitl-mpt1b