Extending linear LAMs to model exogenous state shows standard reconstruction encodes future exogenous info in latent actions, while endogenous-focused spaces and auxiliary objectives like action-supervision enforce consistency across noise.
Oxe-auge: A large-scale robot augmentation of oxe for scaling cross-embodiment policy learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Why Latent Actions Fail, and How to Prevent It
Extending linear LAMs to model exogenous state shows standard reconstruction encodes future exogenous info in latent actions, while endogenous-focused spaces and auxiliary objectives like action-supervision enforce consistency across noise.
-
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.