AI RESEARCH
ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Models
arXiv CS.CL
•
ArXi:2604.09824v1 Announce Type: cross Vision language action (VLA) models enable generalist robotic agents but often exhibit language ignorance, relying on visual shortcuts and remaining insensitive to instruction changes. We present Prospective Grounding and Alignment VLA (ProGAL-VLA), which constructs a 3D entity-centric graph (GSM), uses a slow planner to produce symbolic sub-goals, and aligns them with grounded entities via a Grounding Alignment Contrastive (GAC) loss.