1
UAM: A Dual-Stream Perspective on Forgetting in VLA Training
揭示VLA训练中VLM多模态能力系统退化的“具身税”现象，提出双流新视角UAM
arXiv:2605.15735v1 Announce Type: cross Abstract: Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--langua…