junjin0

/

Multi-view-VLA

like 0

This PR adds a model card for the paper Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation.

The model card includes:

• Metadata for the robotics pipeline tag.
• library_name: peft metadata based on the presence of LoRA adapter configurations.
• Links to the paper, project page, and official GitHub repository.
• A summary of the key innovations: Geometry-Guided Gated Transformer (G3T) and Action Manifold Learning (AML).
• The official BibTeX citation.