AI RESEARCH
SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding
arXiv CS.LG
•
ArXi:2511.17411v2 Announce Type: replace-cross Robotic Foundation Models (RFMs) hold great promise as generalist, end-to-end systems for robot control. Yet their ability to generalize across new environments, tasks, and embodiments remains limited. We argue that a major bottleneck lies in their foundations: most RFMs are built by fine-tuning internet-pretrained Vision-Language Models (VLMs). However, these VLMs are trained on 2D image-language tasks and lack the 3D spatial reasoning inherently required for embodied control in the 3D world.