Flash-WAM: Modality-Aware Distillation for World Action Models 事件

Flash-WAM: Modality-Aware Distillation for World Action Models arXiv:2606.05254v1 Announce Type: cross Abstract: World-action models (WAMs) jointly generate future video and robot actions through iterative diffusion, achieving strong performance on manipulation benchmarks but requiring tens of denoising steps, a cost that precludes real-time control. Step distillation has emerged as the natural remedy, but off-the-shelf methods break down in the joint video-action setting because video and acti