MolmoAct: Action Reasoning Models that can Reason in Space
Paper • 2508.07917 • Published • 45
MolmoAct
All models for the MolmoAct (Multimodal Open Language Model for Action) release.
-
allenai/MolmoAct-7B-D-0812
Robotics • 8B • Updated • 682 • 53Note Our best and demo version of MolmoAct that can be adapted to real world by fine-tuning on your own datasets
allenai/MolmoAct-7B-O-0812
Robotics • 8B • Updated • 30 • 5Note Our most open version of MolmoAct that can be adapt to real world by fine-tuneing on your own datasets
allenai/MolmoAct-7B-D-Pretrain-0812
Robotics • 8B • Updated • 786 • 8Note MolmoAct checkpoint used to replicate zero-shot results on SimplerEnv (Google Robot)
allenai/MolmoAct-7B-D-Pretrain-RT-1-0812
Robotics • 8B • Updated • 546 • 6Note MolmoAct checkpoint used to replicate fine-tuned results on SimplerEnv (Google Robot)
allenai/MolmoAct-7B-D-Captioner-0812
Robotics • 8B • Updated • 18Note MolmoAct checkpoint initialized from Molmo Captioner used to train MolmoAct from scratch
allenai/MolmoAct-7B-D-LIBERO-Spatial-0812
Robotics • 8B • Updated • 456Note MolmoAct checkpoint used to replicate results on LIBERO-Spatial
allenai/MolmoAct-7B-D-LIBERO-Object-0812
Robotics • 8B • Updated • 427Note MolmoAct checkpoint used to replicate results on LIBERO-Object
allenai/MolmoAct-7B-D-LIBERO-Goal-0812
Robotics • 8B • Updated • 450Note MolmoAct checkpoint used to replicate results on LIBERO-Goal
allenai/MolmoAct-7B-D-LIBERO-Long-0812
Robotics • 8B • Updated • 289Note MolmoAct checkpoint used to replicate results on LIBERO-Long