AI RESEARCH
DexHiL: A Human-in-the-Loop Framework for Vision-Language-Action Model Post-Training in Dexterous Manipulation
arXiv CS.AI
•
ArXi:2603.09121v1 Announce Type: cross While Vision-Language-Action (VLA) models have nstrated promising generalization capabilities in robotic manipulation, deploying them on specific and complex downstream tasks still demands effective post-