A new open-world mobile manipulation dataset and a dual-system VLA model show that single-embodiment pre-training, not cross-embodiment pre-training, drives strong downstream task performance.
Integrated task and motion planning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Galaxea Open-World Dataset and G0 Dual-System VLA Model
A new open-world mobile manipulation dataset and a dual-system VLA model show that single-embodiment pre-training, not cross-embodiment pre-training, drives strong downstream task performance.