Keep the Effect, Drop the Actor: Programmable Effect-to-Execution World-Action Models

What happened

arXiv:2610.02398v1 Announce Type: new Abstract: A robot demonstration records two things in the same frames: what happened to the objects, and how one particular arm made it happen. PEWAM, a 71.5M-parameter world-action model, generates effect, robot execution, action and terminal state as four streams with independent flow-matching times, so clamping a program and sampling the execution turns inference into programming, re-solved closed loop from the live scene.

The same program runs on four robot arms without retraining, and after a push, re-solving completes 23 of 60 episodes where replaying the demonstration completes 6. A demonstration is compiled into an effect program: the 3D keypoint trajectories of the objects that moved, two points marking where each was held, and the configuration the scene ends in, with the demonstrator removed. Because a program is a set of coordinates, a person can edit it: the placement follows a shifted terminal state and the grasp turns with rotated contact points.