A video-action foundation model pretrained natively for embodiment achieves few-shot generalization and 225 Hz real-time closed-loop robot control.
Unified video action model
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
-
Native Video-Action Pretraining for Generalizable Robot Control
A video-action foundation model pretrained natively for embodiment achieves few-shot generalization and 225 Hz real-time closed-loop robot control.