Noise Space Learning for VLA Adaptation
From the abstract
Pretrained vision-language-action (VLA) models encode broad manipulation priors, yet adapting them to specific tasks requires balancing limited robot interaction, computational resources, and safety constraints. Noise space learning (NSL) adapts flow-matching-based VLAs by learning a context-conditioned distribution over noise while keeping the pretrained VLA fixed.
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.