arXiv Physical AI

“We introduce NowWAM, a future-target-free co-training formulation that denoises the current observation and predicts robot actions from the same visual stream, directly coupling the native generative objective to the action-facing representation across the denoising trajectory.”

“On the LIBERO-Plus robustness benchmark, NowWAM achieves 87.7% success with the FLUX2-Klein backbone, a 6.1-point improvement over the future-target co-training baseline.”