#machine learning
Sep 2026
SAMBAR: Selective Anchoring via Method of Multipliers for Balanced Knowledge Acquisition and Retention in Vision-Language-Action Models
SMBAR is a continual learning algorithm that prevents catastrophic forgetting during VLA finetuning without requiring access to the demonstrations of any previously learned task, and is cast as a constrained optimization problem and solved with the method of multipliers.
Aayushi Shrivastava, Xunlan Zhou, Hong-Ru Zhao et al.
· arXiv.org · 0 citations