MolmoAct is a 7B robotic foundation model using a three-stage pipeline of depth-aware perception, editable spatial trajectory planning, and low-level action prediction that reports state-of-the-art results on simulation and real-world tasks.
Language Description:Lift up the box Task Progression Score Metrics:Left arm grasp onto the tray (0.3), Right arm grasp onto the tray (0.6), Both arms lift up the tray (1)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MolmoAct: Action Reasoning Models that can Reason in Space
MolmoAct is a 7B robotic foundation model using a three-stage pipeline of depth-aware perception, editable spatial trajectory planning, and low-level action prediction that reports state-of-the-art results on simulation and real-world tasks.