LAR-MoE: Latent-Aligned Routing for Mixture of Experts in Robotic Imitation Learning
LAR-MoE:用于机器人模仿学习中专家混合的潜在对齐路由
机构 * Department of Translational Surgical Oncology, NCT/UCC Dresden(转化外科肿瘤学系) ; Cluster of Excellence-CeTI, TUD, Germany(卓越中心-CeTI) ; Department of Visceral, Thoracic and Vascular Surgery, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD, Germany(visceral、胸腔和血管外科系)
AI总结 LAR-MoE通过潜在对齐路由在机器人模仿学习中实现无监督的专家混合,提升任务适应性和效率。
Comments Submitted to iROS 2026