AI RESEARCH
MSACT: Multistage Spatial Alignment for Stable Low-Latency Fine Manipulation
arXiv CS.CV
•
ArXi:2605.00475v1 Announce Type: cross Real-world fine manipulation, particularly in bimanual manipulation, typically requires low-latency control and stable visual localization, while collecting large-scale data is costly and limited nstrations may lead to localization drift.