AI RESEARCH
PointAction: 3D Points as Universal Action Representations for Robot Control
arXiv CS.LG
•
ArXi:2606.03943v1 Announce Type: cross Video-Action Models (VAMs) leverage the broad visual dynamics captured by pre-trained video diffusion models, offering a promising path toward generalizable robot manipulation. However, RGB-only video rollouts are not directly actionable: they leave metric 3D motion, contact geometry, and fine-grained spatial constraints under-specified, making action grounding ambiguous. Meanwhile, scaling action supervision across diverse tasks and embodiments remains costly.