Open intelligence
for the physical world.

A VLA answers 'what should I do next?'. A world-action model answers 'what happens if I do this?' — and only the second question supports search, recovery, and calibrated refusal. We set out the latent dynamics objective, the rollout-horizon limit that governs it, and how a WAM composes with a VLA rather than replacing it.

A VLA is a vision-language model with the action space bolted onto its output head. We walk through the three design decisions that actually determine whether one works on a real arm — action tokenization, chunking, and the latency budget — and where each of them breaks.