owl10

/

UniDriveVLA_Nusc_Large_Stage3

like 0

This PR adds a comprehensive model card for UniDriveVLA, which is a Unified Driving Vision-Language-Action model.

• It adds the robotics pipeline tag to the metadata for better discoverability.
• It includes links to the research paper, official GitHub repository, and project page.
• It provides a summary of the model's Mixture-of-Transformers architecture and the specialized experts it utilizes.
• It includes the BibTeX citation from the paper.