Third-party test of MolmoAct 2: color-sensitive VLA that still struggles with small-object grasping

YuXiang_IRVL · x · 2026-09-03

The IRVL team ran MolmoAct 2 on their VLA-Replica benchmark setup and shared one successful case. They put "zero-shot" in quotes since the model's training data is unknown.

Preliminary observations:

Original post →

More from Embodied

Embodied channel →