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:
- Which kinds of VLM training benefit VLAs
- Which VLA architecture choices make a difference
- How to train a policy that works immediately in the real world
Their thesis: in robotics, "what we scale" matters as much as "how much we scale."
More from Embodied
- Duke's MARBLE sealed sphere robot rolls by shifting internal weight, works on land and water — lukas_m_ziegler · 2026-09-30
- Astribot releases Lumo-2 tech report: three-stage aligned training, label-free skill transfer — CyberRobooo · 2026-09-30
- Astribot demos two humanoid robots collaborating with its Lumo-2 world-action model — CyberRobooo · 2026-09-30
- Apple's HomePad smart home hub reportedly launches October 13th alongside new HomePod mini and Apple TV — tomwarren · 2026-09-30
- Image Lab Tops Robot Leaderboard: FLUX 3 Action Runs on a Desk-Size Arm — lmoroney · 2026-09-30
- Open-source self-driving guide adds VFH: binning LiDAR into 5° obstacle histograms — 4310sy · 2026-09-30