A dual action alignment framework (latent action world model plus canonical action space) converts heterogeneous human, simulated, and robot data into transferable supervision, with task scores rising monotonically as human ego video increases.
Title resolution pending
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
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
JoyAI-RA 0.5: Scaling Robot Manipulation Learning via Dual Action Alignment
A dual action alignment framework (latent action world model plus canonical action space) converts heterogeneous human, simulated, and robot data into transferable supervision, with task scores rising monotonically as human ego video increases.