ModelMolmoAct2 VLA

MolmoAct2 VLA

A dedicated vision-language-action (VLA) model intended for robot control tasks.

Timeline (last 90 days)

Oct 27

Compared with the dedicated vision-language-action model MolmoAct2 VLA, ZAP's success rate is significantly higher (MolmoAct2 VLA's success rate is only 33.3%).

Unverified50%

All Facts (1)

Unverified

Compared with the dedicated vision-language-action model MolmoAct2 VLA, ZAP's success rate is significantly higher (MolmoAct2 VLA's success rate is only 33.3%).

50%

Source Articles

Pre-training Knows "What," Simulation Teaches "How": ZAP Achieves 96.7% Success Rate with Zero Real-World DataOct 27