A single vision-language-action model jointly trained on recognition and tracking data follows described targets at the best reported levels on a public benchmark and transfers zero-shot from simulation to a real quadruped robot.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TrackVLA: Embodied Visual Tracking in the Wild
A single vision-language-action model jointly trained on recognition and tracking data follows described targets at the best reported levels on a public benchmark and transfers zero-shot from simulation to a real quadruped robot.