ABot-M0 unifies heterogeneous robot data into a 6-million-trajectory dataset and introduces Action Manifold Learning to predict stable actions on a low-dimensional manifold using a DiT backbone.
Starvla: A lego-like codebase for vision-language-action model developing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
ABot-M0 unifies heterogeneous robot data into a 6-million-trajectory dataset and introduces Action Manifold Learning to predict stable actions on a low-dimensional manifold using a DiT backbone.