FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation.

arXiv:2602.13444v2 Announce Type: replace-cross Abstract: Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tasks because the underlying hand-object interaction (HOI) struc