Fully open-source VLA MolmoAct2 lands CoRL 2026 Spotlight, matching π0.5 performance

jmin__cho · x · 2026-09-30

The AI2 team announced that MolmoAct2, a fully open Vision-Language-Action model, has been accepted as a CoRL 2026 Spotlight. All model weights, training code, and data are released, and the policy is built to work out of the box on real robots, matching strong models like π0.5.

The team framed the work around three questions:

Their thesis: in robotics, "what we scale" matters as much as "how much we scale."

Original post →

More from Embodied

Embodied channel →