CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion

作者：Yi Zhang, Yuming Li, Angela P. Schoellig · 单位：Technical University of Munich, Germany, Munich Institute of Robotics and Machine Intelligence (MIRMI), Robotics Institute Germany, Munich Center for Machine Learning · 会议/期刊：arXiv · 日期：2026-01-14 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models for Generalization / Continue Learning