WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation

The potential impacts of world models (WMs, i.e., learned simulators) on robotics are far-reaching—policy evaluation, policy improvement, and test-time planning—all with limited real-world interaction. To unlock these downstream capabilities, a WM needs to jointly satisfy three desiderata: *(i)* fidelity (i.e., producing simulated trajectories that correlate with reality), *(ii)* consistency (i.e., producing simulated trajectories that are coherent over long horizons), and *(iii)* efficiency (i.e., producing simulated trajectories quickly). We propose $\text{WEAVER}$ (World Estimation Across Views for Embodied Reasoning): a WM architecture that simultaneously achieves all three desiderata, providing state-of-the-art results on robotic manipulation tasks. $\text{WEAVER}$ is a multi-view WM trained to predict future latents and reward values via a flow-matching loss. We distill the key design decisions across model architecture, memory, and prediction objectives required to unlock the kinds of long-horizon dynamic manipulation tasks that have confounded prior world modeling approaches. We apply $\text{WEAVER}$ in robotic hardware, demonstrating its effectiveness at policy evaluation ($\rho =0.870$ correlation with real-world success rate), policy improvement (real-world success rate improvement of $38$% on top of the ${\pi }_{0.5}$ robot foundation model), and test-time planning (real-world success rate improvement of $14$% made possible by upto $20\times$ inference speedup over prior WMs). $\text{WEAVER}$ also demonstrates better performance than prior WMs when evaluated on out-of-distribution scenarios. Videos at https://weaver-world-model.github.io.