MVUCF is a training-only method that shapes multi-camera VLA hidden states with depth and cross-view correspondence objectives, improving LIBERO, LIBERO-Plus, and RoboTwin success with no added inference cost.
Proceedings of Robotics: Science and Systems , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-View Unified Camera Fields: Geometry-Shaped Action-Facing Representations for RGB-Only Multi-Camera VLA Policies
MVUCF is a training-only method that shapes multi-camera VLA hidden states with depth and cross-view correspondence objectives, improving LIBERO, LIBERO-Plus, and RoboTwin success with no added inference cost.