AI RESEARCH
CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models
arXiv CS.CV
•
ArXi:2605.10903v1 Announce Type: new This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods with auxiliary