One-shot Human Video-Guided Adaptation for Vision-Language-Action Models
From the abstract
Vision-language-action (VLA) models have recently achieved remarkable progress by leveraging large-scale robot datasets and foundation models for general-purpose robot manipulation. However, their ability to rapidly adapt to novel manipulation tasks beyond the training distribution remains limited.
From the abstract. Our summary is in progress.
The full text is not republished here because the paper's license does not allow it. Read the original on arXiv.