Paper recorded by Signals 4 on 2026-10-05 in cs.CV. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-05 on arXiv · recorded by Signals 4 on 2026-10-06
Category: cs.CV · 计算机视觉 · first seen 2026-10-06
World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mixture-of-Transformers (MoT) architectures and compute video representations once for reuse by the action expert. However, intra-expert iteration (\ie, multi-step action denoising) and inter-expert waiting (\ie, sequential execution of the video and