MolmoAct2 Controls Robotic Arm Zero-Shot

DJiafei · x · 2026-07-10

MolmoAct2 is introduced as an action-inference model capable of running zero-shot on the SO-ARM101 robotic arm, emphasizing that it works out of the box "without any training."

It has now been integrated into LeRobot, covering the entire pipeline:

Technically, it combines the Molmo2-ER vision-language backbone with a flow-matching action expert, translating images, language, and embodiment states into action chunks. The post also details the hardware requirements: bf16 inference takes about 12GB of VRAM, LoRA fine-tuning can be done on a single 24GB GPU, and calibration corrections are already built into the checkpoint.

Original post →

More from Embodied

Embodied channel →