AI RESEARCH
IROSA: Interactive Robot Skill Adaptation using Natural Language
arXiv CS.AI
•
ArXi:2603.03897v2 Announce Type: replace-cross Foundation models have nstrated impressive capabilities across diverse domains, while imitation learning provides principled methods for robot skill adaptation from limited data. Combining these approaches holds significant promise for direct application to robotics, yet this combination has received limited attention, particularly for industrial deployment.